| { |
| "metadata": { |
| "total_parameters": 5763569630, |
| "total_size": 23054459032 |
| }, |
| "weight_map": { |
| "model.audio_adapter.adapters.muq.layer_fusion.layer_weights": "model-00005-of-00005.safetensors", |
| "model.audio_adapter.adapters.sslam.layer_fusion.layer_weights": "model-00005-of-00005.safetensors", |
| "model.audio_adapter.adapters.w2vbert.layer_fusion.layer_weights": "model-00005-of-00005.safetensors", |
| "model.audio_adapter.adapters.whisper.adapter.downsampler.0.0.bias": "model-00005-of-00005.safetensors", |
| "model.audio_adapter.adapters.whisper.adapter.downsampler.0.0.weight": "model-00005-of-00005.safetensors", |
| "model.audio_adapter.adapters.whisper.adapter.downsampler.0.2.bias": "model-00005-of-00005.safetensors", |
| "model.audio_adapter.adapters.whisper.adapter.downsampler.0.2.num_batches_tracked": "model-00005-of-00005.safetensors", |
| "model.audio_adapter.adapters.whisper.adapter.downsampler.0.2.running_mean": "model-00005-of-00005.safetensors", |
| "model.audio_adapter.adapters.whisper.adapter.downsampler.0.2.running_var": "model-00005-of-00005.safetensors", |
| "model.audio_adapter.adapters.whisper.adapter.downsampler.0.2.weight": "model-00005-of-00005.safetensors", |
| "model.audio_adapter.adapters.whisper.adapter.downsampler.1.0.bias": "model-00005-of-00005.safetensors", |
| "model.audio_adapter.adapters.whisper.adapter.downsampler.1.0.weight": "model-00005-of-00005.safetensors", |
| "model.audio_adapter.adapters.whisper.adapter.downsampler.1.2.bias": "model-00005-of-00005.safetensors", |
| "model.audio_adapter.adapters.whisper.adapter.downsampler.1.2.num_batches_tracked": "model-00005-of-00005.safetensors", |
| "model.audio_adapter.adapters.whisper.adapter.downsampler.1.2.running_mean": "model-00005-of-00005.safetensors", |
| "model.audio_adapter.adapters.whisper.adapter.downsampler.1.2.running_var": "model-00005-of-00005.safetensors", |
| "model.audio_adapter.adapters.whisper.adapter.downsampler.1.2.weight": "model-00005-of-00005.safetensors", |
| "model.audio_adapter.adapters.whisper.adapter.input_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_adapter.adapters.whisper.adapter.input_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_adapter.adapters.whisper.layer_fusion.layer_weights": "model-00005-of-00005.safetensors", |
| "model.audio_adapter.adapters.whisper.llm_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_adapter.adapters.whisper.llm_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.cls_token": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.embed_positions.inv_freq": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.0.conv_module.batch_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.0.conv_module.batch_norm.num_batches_tracked": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.0.conv_module.batch_norm.running_mean": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.0.conv_module.batch_norm.running_var": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.0.conv_module.batch_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.0.conv_module.depthwise_conv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.0.conv_module.layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.0.conv_module.layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.0.conv_module.pointwise_conv1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.0.conv_module.pointwise_conv2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.0.ffn1.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.0.ffn1.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.0.ffn1.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.0.ffn1.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.0.ffn1_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.0.ffn1_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.0.ffn2.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.0.ffn2.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.0.ffn2.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.0.ffn2.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.0.ffn2_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.0.ffn2_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.0.final_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.0.final_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.0.self_attn.linear_k.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.0.self_attn.linear_k.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.0.self_attn.linear_out.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.0.self_attn.linear_out.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.0.self_attn.linear_q.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.0.self_attn.linear_q.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.0.self_attn.linear_v.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.0.self_attn.linear_v.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.0.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.0.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.1.conv_module.batch_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.1.conv_module.batch_norm.num_batches_tracked": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.1.conv_module.batch_norm.running_mean": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.1.conv_module.batch_norm.running_var": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.1.conv_module.batch_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.1.conv_module.depthwise_conv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.1.conv_module.layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.1.conv_module.layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.1.conv_module.pointwise_conv1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.1.conv_module.pointwise_conv2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.1.ffn1.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.1.ffn1.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.1.ffn1.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.1.ffn1.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.1.ffn1_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.1.ffn1_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.1.ffn2.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.1.ffn2.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.1.ffn2.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.1.ffn2.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.1.ffn2_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.1.ffn2_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.1.final_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.1.final_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.1.self_attn.linear_k.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.1.self_attn.linear_k.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.1.self_attn.linear_out.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.1.self_attn.linear_out.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.1.self_attn.linear_q.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.1.self_attn.linear_q.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.1.self_attn.linear_v.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.1.self_attn.linear_v.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.1.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.1.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.10.conv_module.batch_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.10.conv_module.batch_norm.num_batches_tracked": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.10.conv_module.batch_norm.running_mean": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.10.conv_module.batch_norm.running_var": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.10.conv_module.batch_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.10.conv_module.depthwise_conv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.10.conv_module.layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.10.conv_module.layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.10.conv_module.pointwise_conv1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.10.conv_module.pointwise_conv2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.10.ffn1.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.10.ffn1.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.10.ffn1.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.10.ffn1.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.10.ffn1_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.10.ffn1_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.10.ffn2.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.10.ffn2.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.10.ffn2.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.10.ffn2.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.10.ffn2_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.10.ffn2_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.10.final_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.10.final_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.10.self_attn.linear_k.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.10.self_attn.linear_k.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.10.self_attn.linear_out.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.10.self_attn.linear_out.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.10.self_attn.linear_q.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.10.self_attn.linear_q.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.10.self_attn.linear_v.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.10.self_attn.linear_v.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.10.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.10.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.11.conv_module.batch_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.11.conv_module.batch_norm.num_batches_tracked": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.11.conv_module.batch_norm.running_mean": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.11.conv_module.batch_norm.running_var": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.11.conv_module.batch_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.11.conv_module.depthwise_conv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.11.conv_module.layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.11.conv_module.layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.11.conv_module.pointwise_conv1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.11.conv_module.pointwise_conv2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.11.ffn1.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.11.ffn1.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.11.ffn1.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.11.ffn1.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.11.ffn1_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.11.ffn1_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.11.ffn2.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.11.ffn2.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.11.ffn2.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.11.ffn2.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.11.ffn2_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.11.ffn2_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.11.final_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.11.final_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.11.self_attn.linear_k.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.11.self_attn.linear_k.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.11.self_attn.linear_out.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.11.self_attn.linear_out.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.11.self_attn.linear_q.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.11.self_attn.linear_q.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.11.self_attn.linear_v.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.11.self_attn.linear_v.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.11.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.11.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.2.conv_module.batch_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.2.conv_module.batch_norm.num_batches_tracked": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.2.conv_module.batch_norm.running_mean": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.2.conv_module.batch_norm.running_var": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.2.conv_module.batch_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.2.conv_module.depthwise_conv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.2.conv_module.layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.2.conv_module.layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.2.conv_module.pointwise_conv1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.2.conv_module.pointwise_conv2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.2.ffn1.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.2.ffn1.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.2.ffn1.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.2.ffn1.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.2.ffn1_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.2.ffn1_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.2.ffn2.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.2.ffn2.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.2.ffn2.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.2.ffn2.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.2.ffn2_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.2.ffn2_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.2.final_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.2.final_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.2.self_attn.linear_k.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.2.self_attn.linear_k.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.2.self_attn.linear_out.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.2.self_attn.linear_out.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.2.self_attn.linear_q.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.2.self_attn.linear_q.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.2.self_attn.linear_v.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.2.self_attn.linear_v.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.2.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.2.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.3.conv_module.batch_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.3.conv_module.batch_norm.num_batches_tracked": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.3.conv_module.batch_norm.running_mean": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.3.conv_module.batch_norm.running_var": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.3.conv_module.batch_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.3.conv_module.depthwise_conv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.3.conv_module.layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.3.conv_module.layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.3.conv_module.pointwise_conv1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.3.conv_module.pointwise_conv2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.3.ffn1.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.3.ffn1.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.3.ffn1.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.3.ffn1.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.3.ffn1_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.3.ffn1_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.3.ffn2.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.3.ffn2.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.3.ffn2.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.3.ffn2.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.3.ffn2_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.3.ffn2_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.3.final_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.3.final_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.3.self_attn.linear_k.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.3.self_attn.linear_k.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.3.self_attn.linear_out.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.3.self_attn.linear_out.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.3.self_attn.linear_q.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.3.self_attn.linear_q.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.3.self_attn.linear_v.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.3.self_attn.linear_v.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.3.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.3.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.4.conv_module.batch_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.4.conv_module.batch_norm.num_batches_tracked": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.4.conv_module.batch_norm.running_mean": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.4.conv_module.batch_norm.running_var": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.4.conv_module.batch_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.4.conv_module.depthwise_conv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.4.conv_module.layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.4.conv_module.layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.4.conv_module.pointwise_conv1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.4.conv_module.pointwise_conv2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.4.ffn1.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.4.ffn1.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.4.ffn1.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.4.ffn1.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.4.ffn1_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.4.ffn1_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.4.ffn2.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.4.ffn2.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.4.ffn2.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.4.ffn2.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.4.ffn2_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.4.ffn2_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.4.final_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.4.final_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.4.self_attn.linear_k.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.4.self_attn.linear_k.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.4.self_attn.linear_out.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.4.self_attn.linear_out.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.4.self_attn.linear_q.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.4.self_attn.linear_q.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.4.self_attn.linear_v.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.4.self_attn.linear_v.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.4.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.4.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.5.conv_module.batch_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.5.conv_module.batch_norm.num_batches_tracked": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.5.conv_module.batch_norm.running_mean": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.5.conv_module.batch_norm.running_var": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.5.conv_module.batch_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.5.conv_module.depthwise_conv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.5.conv_module.layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.5.conv_module.layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.5.conv_module.pointwise_conv1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.5.conv_module.pointwise_conv2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.5.ffn1.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.5.ffn1.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.5.ffn1.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.5.ffn1.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.5.ffn1_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.5.ffn1_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.5.ffn2.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.5.ffn2.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.5.ffn2.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.5.ffn2.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.5.ffn2_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.5.ffn2_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.5.final_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.5.final_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.5.self_attn.linear_k.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.5.self_attn.linear_k.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.5.self_attn.linear_out.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.5.self_attn.linear_out.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.5.self_attn.linear_q.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.5.self_attn.linear_q.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.5.self_attn.linear_v.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.5.self_attn.linear_v.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.5.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.5.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.6.conv_module.batch_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.6.conv_module.batch_norm.num_batches_tracked": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.6.conv_module.batch_norm.running_mean": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.6.conv_module.batch_norm.running_var": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.6.conv_module.batch_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.6.conv_module.depthwise_conv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.6.conv_module.layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.6.conv_module.layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.6.conv_module.pointwise_conv1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.6.conv_module.pointwise_conv2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.6.ffn1.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.6.ffn1.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.6.ffn1.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.6.ffn1.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.6.ffn1_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.6.ffn1_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.6.ffn2.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.6.ffn2.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.6.ffn2.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.6.ffn2.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.6.ffn2_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.6.ffn2_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.6.final_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.6.final_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.6.self_attn.linear_k.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.6.self_attn.linear_k.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.6.self_attn.linear_out.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.6.self_attn.linear_out.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.6.self_attn.linear_q.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.6.self_attn.linear_q.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.6.self_attn.linear_v.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.6.self_attn.linear_v.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.6.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.6.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.7.conv_module.batch_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.7.conv_module.batch_norm.num_batches_tracked": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.7.conv_module.batch_norm.running_mean": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.7.conv_module.batch_norm.running_var": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.7.conv_module.batch_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.7.conv_module.depthwise_conv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.7.conv_module.layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.7.conv_module.layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.7.conv_module.pointwise_conv1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.7.conv_module.pointwise_conv2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.7.ffn1.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.7.ffn1.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.7.ffn1.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.7.ffn1.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.7.ffn1_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.7.ffn1_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.7.ffn2.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.7.ffn2.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.7.ffn2.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.7.ffn2.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.7.ffn2_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.7.ffn2_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.7.final_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.7.final_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.7.self_attn.linear_k.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.7.self_attn.linear_k.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.7.self_attn.linear_out.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.7.self_attn.linear_out.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.7.self_attn.linear_q.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.7.self_attn.linear_q.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.7.self_attn.linear_v.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.7.self_attn.linear_v.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.7.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.7.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.8.conv_module.batch_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.8.conv_module.batch_norm.num_batches_tracked": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.8.conv_module.batch_norm.running_mean": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.8.conv_module.batch_norm.running_var": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.8.conv_module.batch_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.8.conv_module.depthwise_conv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.8.conv_module.layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.8.conv_module.layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.8.conv_module.pointwise_conv1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.8.conv_module.pointwise_conv2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.8.ffn1.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.8.ffn1.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.8.ffn1.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.8.ffn1.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.8.ffn1_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.8.ffn1_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.8.ffn2.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.8.ffn2.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.8.ffn2.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.8.ffn2.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.8.ffn2_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.8.ffn2_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.8.final_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.8.final_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.8.self_attn.linear_k.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.8.self_attn.linear_k.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.8.self_attn.linear_out.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.8.self_attn.linear_out.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.8.self_attn.linear_q.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.8.self_attn.linear_q.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.8.self_attn.linear_v.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.8.self_attn.linear_v.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.8.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.8.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.9.conv_module.batch_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.9.conv_module.batch_norm.num_batches_tracked": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.9.conv_module.batch_norm.running_mean": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.9.conv_module.batch_norm.running_var": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.9.conv_module.batch_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.9.conv_module.depthwise_conv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.9.conv_module.layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.9.conv_module.layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.9.conv_module.pointwise_conv1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.9.conv_module.pointwise_conv2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.9.ffn1.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.9.ffn1.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.9.ffn1.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.9.ffn1.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.9.ffn1_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.9.ffn1_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.9.ffn2.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.9.ffn2.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.9.ffn2.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.9.ffn2.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.9.ffn2_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.9.ffn2_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.9.final_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.9.final_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.9.self_attn.linear_k.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.9.self_attn.linear_k.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.9.self_attn.linear_out.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.9.self_attn.linear_out.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.9.self_attn.linear_q.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.9.self_attn.linear_q.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.9.self_attn.linear_v.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.9.self_attn.linear_v.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.9.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.layers.9.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.pos_conv_embed.conv.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.pos_conv_embed.conv.parametrizations.weight.original0": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conformer.pos_conv_embed.conv.parametrizations.weight.original1": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.0.bn1.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.0.bn1.num_batches_tracked": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.0.bn1.running_mean": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.0.bn1.running_var": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.0.bn1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.0.bn2.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.0.bn2.num_batches_tracked": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.0.bn2.running_mean": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.0.bn2.running_var": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.0.bn2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.0.bn3.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.0.bn3.num_batches_tracked": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.0.bn3.running_mean": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.0.bn3.running_var": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.0.bn3.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.0.conv1.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.0.conv1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.0.conv2.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.0.conv2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.0.conv3.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.0.conv3.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.1.bn1.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.1.bn1.num_batches_tracked": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.1.bn1.running_mean": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.1.bn1.running_var": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.1.bn1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.1.bn2.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.1.bn2.num_batches_tracked": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.1.bn2.running_mean": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.1.bn2.running_var": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.1.bn2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.1.bn3.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.1.bn3.num_batches_tracked": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.1.bn3.running_mean": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.1.bn3.running_var": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.1.bn3.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.1.conv1.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.1.conv1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.1.conv2.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.1.conv2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.1.conv3.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.conv.1.conv3.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.linear.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.conv.linear.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.linear.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.linear.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.0.codebook.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.0.in_proj.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.0.in_proj.weight_g": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.0.in_proj.weight_v": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.0.out_proj.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.0.out_proj.weight_g": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.0.out_proj.weight_v": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.0.stale_counter": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.1.codebook.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.1.in_proj.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.1.in_proj.weight_g": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.1.in_proj.weight_v": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.1.out_proj.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.1.out_proj.weight_g": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.1.out_proj.weight_v": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.1.stale_counter": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.2.codebook.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.2.in_proj.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.2.in_proj.weight_g": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.2.in_proj.weight_v": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.2.out_proj.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.2.out_proj.weight_g": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.2.out_proj.weight_v": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.2.stale_counter": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.3.codebook.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.3.in_proj.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.3.in_proj.weight_g": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.3.in_proj.weight_v": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.3.out_proj.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.3.out_proj.weight_g": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.3.out_proj.weight_v": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.3.stale_counter": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.4.codebook.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.4.in_proj.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.4.in_proj.weight_g": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.4.in_proj.weight_v": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.4.out_proj.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.4.out_proj.weight_g": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.4.out_proj.weight_v": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.4.stale_counter": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.5.codebook.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.5.in_proj.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.5.in_proj.weight_g": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.5.in_proj.weight_v": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.5.out_proj.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.5.out_proj.weight_g": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.5.out_proj.weight_v": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.5.stale_counter": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.6.codebook.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.6.in_proj.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.6.in_proj.weight_g": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.6.in_proj.weight_v": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.6.out_proj.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.6.out_proj.weight_g": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.6.out_proj.weight_v": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.6.stale_counter": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.7.codebook.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.7.in_proj.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.7.in_proj.weight_g": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.7.in_proj.weight_v": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.7.out_proj.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.7.out_proj.weight_g": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.7.out_proj.weight_v": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.muq.encoder.model.rvq.quantizers.7.stale_counter": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.0.attn.proj.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.0.attn.proj.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.0.attn.qkv.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.0.attn.qkv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.0.mlp.fc1.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.0.mlp.fc1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.0.mlp.fc2.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.0.mlp.fc2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.0.norm1.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.0.norm1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.0.norm2.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.0.norm2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.1.attn.proj.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.1.attn.proj.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.1.attn.qkv.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.1.attn.qkv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.1.mlp.fc1.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.1.mlp.fc1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.1.mlp.fc2.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.1.mlp.fc2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.1.norm1.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.1.norm1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.1.norm2.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.1.norm2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.10.attn.proj.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.10.attn.proj.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.10.attn.qkv.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.10.attn.qkv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.10.mlp.fc1.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.10.mlp.fc1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.10.mlp.fc2.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.10.mlp.fc2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.10.norm1.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.10.norm1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.10.norm2.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.10.norm2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.11.attn.proj.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.11.attn.proj.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.11.attn.qkv.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.11.attn.qkv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.11.mlp.fc1.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.11.mlp.fc1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.11.mlp.fc2.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.11.mlp.fc2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.11.norm1.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.11.norm1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.11.norm2.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.11.norm2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.2.attn.proj.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.2.attn.proj.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.2.attn.qkv.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.2.attn.qkv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.2.mlp.fc1.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.2.mlp.fc1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.2.mlp.fc2.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.2.mlp.fc2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.2.norm1.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.2.norm1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.2.norm2.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.2.norm2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.3.attn.proj.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.3.attn.proj.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.3.attn.qkv.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.3.attn.qkv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.3.mlp.fc1.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.3.mlp.fc1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.3.mlp.fc2.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.3.mlp.fc2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.3.norm1.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.3.norm1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.3.norm2.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.3.norm2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.4.attn.proj.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.4.attn.proj.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.4.attn.qkv.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.4.attn.qkv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.4.mlp.fc1.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.4.mlp.fc1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.4.mlp.fc2.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.4.mlp.fc2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.4.norm1.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.4.norm1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.4.norm2.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.4.norm2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.5.attn.proj.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.5.attn.proj.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.5.attn.qkv.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.5.attn.qkv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.5.mlp.fc1.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.5.mlp.fc1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.5.mlp.fc2.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.5.mlp.fc2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.5.norm1.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.5.norm1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.5.norm2.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.5.norm2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.6.attn.proj.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.6.attn.proj.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.6.attn.qkv.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.6.attn.qkv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.6.mlp.fc1.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.6.mlp.fc1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.6.mlp.fc2.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.6.mlp.fc2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.6.norm1.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.6.norm1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.6.norm2.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.6.norm2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.7.attn.proj.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.7.attn.proj.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.7.attn.qkv.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.7.attn.qkv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.7.mlp.fc1.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.7.mlp.fc1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.7.mlp.fc2.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.7.mlp.fc2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.7.norm1.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.7.norm1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.7.norm2.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.7.norm2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.8.attn.proj.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.8.attn.proj.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.8.attn.qkv.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.8.attn.qkv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.8.mlp.fc1.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.8.mlp.fc1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.8.mlp.fc2.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.8.mlp.fc2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.8.norm1.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.8.norm1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.8.norm2.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.8.norm2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.9.attn.proj.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.9.attn.proj.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.9.attn.qkv.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.9.attn.qkv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.9.mlp.fc1.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.9.mlp.fc1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.9.mlp.fc2.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.9.mlp.fc2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.9.norm1.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.9.norm1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.9.norm2.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.blocks.9.norm2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.extra_tokens": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.fc_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.fc_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.fixed_positional_encoder.positions": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.head.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.head.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.local_encoder.proj.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.local_encoder.proj.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.pre_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.sslam.encoder.model.pre_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.0.conv_module.depthwise_conv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.0.conv_module.depthwise_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.0.conv_module.depthwise_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.0.conv_module.layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.0.conv_module.layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.0.conv_module.pointwise_conv1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.0.conv_module.pointwise_conv2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.0.ffn1.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.0.ffn1.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.0.ffn1.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.0.ffn1.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.0.ffn1_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.0.ffn1_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.0.ffn2.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.0.ffn2.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.0.ffn2.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.0.ffn2.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.0.ffn2_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.0.ffn2_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.0.final_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.0.final_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.0.self_attn.distance_embedding.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.0.self_attn.linear_k.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.0.self_attn.linear_k.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.0.self_attn.linear_out.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.0.self_attn.linear_out.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.0.self_attn.linear_q.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.0.self_attn.linear_q.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.0.self_attn.linear_v.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.0.self_attn.linear_v.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.0.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.0.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.1.conv_module.depthwise_conv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.1.conv_module.depthwise_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.1.conv_module.depthwise_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.1.conv_module.layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.1.conv_module.layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.1.conv_module.pointwise_conv1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.1.conv_module.pointwise_conv2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.1.ffn1.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.1.ffn1.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.1.ffn1.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.1.ffn1.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.1.ffn1_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.1.ffn1_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.1.ffn2.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.1.ffn2.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.1.ffn2.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.1.ffn2.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.1.ffn2_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.1.ffn2_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.1.final_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.1.final_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.1.self_attn.distance_embedding.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.1.self_attn.linear_k.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.1.self_attn.linear_k.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.1.self_attn.linear_out.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.1.self_attn.linear_out.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.1.self_attn.linear_q.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.1.self_attn.linear_q.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.1.self_attn.linear_v.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.1.self_attn.linear_v.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.1.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.1.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.10.conv_module.depthwise_conv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.10.conv_module.depthwise_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.10.conv_module.depthwise_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.10.conv_module.layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.10.conv_module.layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.10.conv_module.pointwise_conv1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.10.conv_module.pointwise_conv2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.10.ffn1.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.10.ffn1.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.10.ffn1.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.10.ffn1.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.10.ffn1_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.10.ffn1_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.10.ffn2.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.10.ffn2.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.10.ffn2.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.10.ffn2.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.10.ffn2_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.10.ffn2_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.10.final_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.10.final_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.10.self_attn.distance_embedding.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.10.self_attn.linear_k.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.10.self_attn.linear_k.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.10.self_attn.linear_out.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.10.self_attn.linear_out.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.10.self_attn.linear_q.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.10.self_attn.linear_q.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.10.self_attn.linear_v.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.10.self_attn.linear_v.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.10.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.10.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.11.conv_module.depthwise_conv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.11.conv_module.depthwise_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.11.conv_module.depthwise_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.11.conv_module.layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.11.conv_module.layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.11.conv_module.pointwise_conv1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.11.conv_module.pointwise_conv2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.11.ffn1.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.11.ffn1.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.11.ffn1.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.11.ffn1.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.11.ffn1_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.11.ffn1_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.11.ffn2.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.11.ffn2.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.11.ffn2.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.11.ffn2.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.11.ffn2_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.11.ffn2_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.11.final_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.11.final_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.11.self_attn.distance_embedding.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.11.self_attn.linear_k.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.11.self_attn.linear_k.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.11.self_attn.linear_out.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.11.self_attn.linear_out.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.11.self_attn.linear_q.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.11.self_attn.linear_q.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.11.self_attn.linear_v.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.11.self_attn.linear_v.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.11.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.11.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.12.conv_module.depthwise_conv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.12.conv_module.depthwise_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.12.conv_module.depthwise_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.12.conv_module.layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.12.conv_module.layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.12.conv_module.pointwise_conv1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.12.conv_module.pointwise_conv2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.12.ffn1.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.12.ffn1.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.12.ffn1.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.12.ffn1.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.12.ffn1_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.12.ffn1_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.12.ffn2.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.12.ffn2.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.12.ffn2.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.12.ffn2.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.12.ffn2_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.12.ffn2_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.12.final_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.12.final_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.12.self_attn.distance_embedding.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.12.self_attn.linear_k.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.12.self_attn.linear_k.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.12.self_attn.linear_out.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.12.self_attn.linear_out.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.12.self_attn.linear_q.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.12.self_attn.linear_q.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.12.self_attn.linear_v.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.12.self_attn.linear_v.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.12.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.12.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.13.conv_module.depthwise_conv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.13.conv_module.depthwise_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.13.conv_module.depthwise_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.13.conv_module.layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.13.conv_module.layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.13.conv_module.pointwise_conv1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.13.conv_module.pointwise_conv2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.13.ffn1.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.13.ffn1.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.13.ffn1.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.13.ffn1.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.13.ffn1_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.13.ffn1_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.13.ffn2.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.13.ffn2.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.13.ffn2.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.13.ffn2.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.13.ffn2_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.13.ffn2_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.13.final_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.13.final_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.13.self_attn.distance_embedding.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.13.self_attn.linear_k.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.13.self_attn.linear_k.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.13.self_attn.linear_out.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.13.self_attn.linear_out.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.13.self_attn.linear_q.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.13.self_attn.linear_q.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.13.self_attn.linear_v.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.13.self_attn.linear_v.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.13.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.13.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.14.conv_module.depthwise_conv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.14.conv_module.depthwise_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.14.conv_module.depthwise_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.14.conv_module.layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.14.conv_module.layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.14.conv_module.pointwise_conv1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.14.conv_module.pointwise_conv2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.14.ffn1.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.14.ffn1.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.14.ffn1.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.14.ffn1.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.14.ffn1_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.14.ffn1_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.14.ffn2.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.14.ffn2.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.14.ffn2.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.14.ffn2.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.14.ffn2_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.14.ffn2_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.14.final_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.14.final_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.14.self_attn.distance_embedding.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.14.self_attn.linear_k.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.14.self_attn.linear_k.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.14.self_attn.linear_out.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.14.self_attn.linear_out.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.14.self_attn.linear_q.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.14.self_attn.linear_q.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.14.self_attn.linear_v.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.14.self_attn.linear_v.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.14.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.14.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.15.conv_module.depthwise_conv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.15.conv_module.depthwise_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.15.conv_module.depthwise_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.15.conv_module.layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.15.conv_module.layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.15.conv_module.pointwise_conv1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.15.conv_module.pointwise_conv2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.15.ffn1.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.15.ffn1.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.15.ffn1.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.15.ffn1.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.15.ffn1_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.15.ffn1_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.15.ffn2.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.15.ffn2.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.15.ffn2.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.15.ffn2.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.15.ffn2_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.15.ffn2_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.15.final_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.15.final_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.15.self_attn.distance_embedding.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.15.self_attn.linear_k.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.15.self_attn.linear_k.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.15.self_attn.linear_out.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.15.self_attn.linear_out.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.15.self_attn.linear_q.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.15.self_attn.linear_q.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.15.self_attn.linear_v.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.15.self_attn.linear_v.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.15.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.15.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.16.conv_module.depthwise_conv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.16.conv_module.depthwise_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.16.conv_module.depthwise_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.16.conv_module.layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.16.conv_module.layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.16.conv_module.pointwise_conv1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.16.conv_module.pointwise_conv2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.16.ffn1.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.16.ffn1.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.16.ffn1.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.16.ffn1.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.16.ffn1_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.16.ffn1_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.16.ffn2.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.16.ffn2.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.16.ffn2.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.16.ffn2.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.16.ffn2_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.16.ffn2_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.16.final_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.16.final_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.16.self_attn.distance_embedding.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.16.self_attn.linear_k.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.16.self_attn.linear_k.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.16.self_attn.linear_out.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.16.self_attn.linear_out.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.16.self_attn.linear_q.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.16.self_attn.linear_q.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.16.self_attn.linear_v.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.16.self_attn.linear_v.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.16.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.16.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.17.conv_module.depthwise_conv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.17.conv_module.depthwise_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.17.conv_module.depthwise_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.17.conv_module.layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.17.conv_module.layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.17.conv_module.pointwise_conv1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.17.conv_module.pointwise_conv2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.17.ffn1.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.17.ffn1.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.17.ffn1.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.17.ffn1.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.17.ffn1_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.17.ffn1_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.17.ffn2.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.17.ffn2.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.17.ffn2.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.17.ffn2.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.17.ffn2_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.17.ffn2_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.17.final_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.17.final_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.17.self_attn.distance_embedding.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.17.self_attn.linear_k.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.17.self_attn.linear_k.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.17.self_attn.linear_out.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.17.self_attn.linear_out.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.17.self_attn.linear_q.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.17.self_attn.linear_q.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.17.self_attn.linear_v.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.17.self_attn.linear_v.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.17.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.17.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.18.conv_module.depthwise_conv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.18.conv_module.depthwise_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.18.conv_module.depthwise_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.18.conv_module.layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.18.conv_module.layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.18.conv_module.pointwise_conv1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.18.conv_module.pointwise_conv2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.18.ffn1.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.18.ffn1.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.18.ffn1.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.18.ffn1.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.18.ffn1_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.18.ffn1_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.18.ffn2.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.18.ffn2.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.18.ffn2.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.18.ffn2.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.18.ffn2_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.18.ffn2_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.18.final_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.18.final_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.18.self_attn.distance_embedding.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.18.self_attn.linear_k.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.18.self_attn.linear_k.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.18.self_attn.linear_out.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.18.self_attn.linear_out.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.18.self_attn.linear_q.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.18.self_attn.linear_q.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.18.self_attn.linear_v.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.18.self_attn.linear_v.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.18.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.18.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.19.conv_module.depthwise_conv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.19.conv_module.depthwise_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.19.conv_module.depthwise_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.19.conv_module.layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.19.conv_module.layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.19.conv_module.pointwise_conv1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.19.conv_module.pointwise_conv2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.19.ffn1.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.19.ffn1.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.19.ffn1.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.19.ffn1.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.19.ffn1_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.19.ffn1_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.19.ffn2.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.19.ffn2.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.19.ffn2.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.19.ffn2.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.19.ffn2_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.19.ffn2_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.19.final_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.19.final_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.19.self_attn.distance_embedding.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.19.self_attn.linear_k.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.19.self_attn.linear_k.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.19.self_attn.linear_out.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.19.self_attn.linear_out.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.19.self_attn.linear_q.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.19.self_attn.linear_q.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.19.self_attn.linear_v.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.19.self_attn.linear_v.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.19.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.19.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.2.conv_module.depthwise_conv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.2.conv_module.depthwise_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.2.conv_module.depthwise_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.2.conv_module.layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.2.conv_module.layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.2.conv_module.pointwise_conv1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.2.conv_module.pointwise_conv2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.2.ffn1.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.2.ffn1.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.2.ffn1.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.2.ffn1.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.2.ffn1_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.2.ffn1_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.2.ffn2.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.2.ffn2.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.2.ffn2.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.2.ffn2.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.2.ffn2_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.2.ffn2_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.2.final_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.2.final_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.2.self_attn.distance_embedding.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.2.self_attn.linear_k.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.2.self_attn.linear_k.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.2.self_attn.linear_out.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.2.self_attn.linear_out.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.2.self_attn.linear_q.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.2.self_attn.linear_q.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.2.self_attn.linear_v.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.2.self_attn.linear_v.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.2.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.2.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.20.conv_module.depthwise_conv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.20.conv_module.depthwise_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.20.conv_module.depthwise_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.20.conv_module.layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.20.conv_module.layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.20.conv_module.pointwise_conv1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.20.conv_module.pointwise_conv2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.20.ffn1.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.20.ffn1.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.20.ffn1.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.20.ffn1.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.20.ffn1_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.20.ffn1_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.20.ffn2.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.20.ffn2.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.20.ffn2.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.20.ffn2.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.20.ffn2_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.20.ffn2_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.20.final_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.20.final_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.20.self_attn.distance_embedding.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.20.self_attn.linear_k.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.20.self_attn.linear_k.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.20.self_attn.linear_out.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.20.self_attn.linear_out.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.20.self_attn.linear_q.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.20.self_attn.linear_q.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.20.self_attn.linear_v.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.20.self_attn.linear_v.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.20.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.20.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.21.conv_module.depthwise_conv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.21.conv_module.depthwise_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.21.conv_module.depthwise_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.21.conv_module.layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.21.conv_module.layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.21.conv_module.pointwise_conv1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.21.conv_module.pointwise_conv2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.21.ffn1.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.21.ffn1.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.21.ffn1.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.21.ffn1.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.21.ffn1_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.21.ffn1_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.21.ffn2.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.21.ffn2.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.21.ffn2.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.21.ffn2.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.21.ffn2_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.21.ffn2_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.21.final_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.21.final_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.21.self_attn.distance_embedding.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.21.self_attn.linear_k.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.21.self_attn.linear_k.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.21.self_attn.linear_out.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.21.self_attn.linear_out.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.21.self_attn.linear_q.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.21.self_attn.linear_q.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.21.self_attn.linear_v.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.21.self_attn.linear_v.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.21.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.21.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.22.conv_module.depthwise_conv.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.22.conv_module.depthwise_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.22.conv_module.depthwise_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.22.conv_module.layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.22.conv_module.layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.22.conv_module.pointwise_conv1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.22.conv_module.pointwise_conv2.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.22.ffn1.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.22.ffn1.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.22.ffn1.output_dense.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.22.ffn1.output_dense.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.22.ffn1_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.22.ffn1_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.22.ffn2.intermediate_dense.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.22.ffn2.intermediate_dense.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.22.ffn2.output_dense.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.22.ffn2.output_dense.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.22.ffn2_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.22.ffn2_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.22.final_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.22.final_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.22.self_attn.distance_embedding.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.22.self_attn.linear_k.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.22.self_attn.linear_k.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.22.self_attn.linear_out.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.22.self_attn.linear_out.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.22.self_attn.linear_q.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.22.self_attn.linear_q.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.22.self_attn.linear_v.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.22.self_attn.linear_v.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.22.self_attn_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.22.self_attn_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.23.conv_module.depthwise_conv.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.23.conv_module.depthwise_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.23.conv_module.depthwise_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.23.conv_module.layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.23.conv_module.layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.23.conv_module.pointwise_conv1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.23.conv_module.pointwise_conv2.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.23.ffn1.intermediate_dense.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.23.ffn1.intermediate_dense.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.23.ffn1.output_dense.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.23.ffn1.output_dense.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.23.ffn1_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.23.ffn1_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.23.ffn2.intermediate_dense.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.23.ffn2.intermediate_dense.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.23.ffn2.output_dense.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.23.ffn2.output_dense.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.23.ffn2_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.23.ffn2_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.23.final_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.23.final_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.23.self_attn.distance_embedding.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.23.self_attn.linear_k.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.23.self_attn.linear_k.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.23.self_attn.linear_out.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.23.self_attn.linear_out.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.23.self_attn.linear_q.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.23.self_attn.linear_q.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.23.self_attn.linear_v.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.23.self_attn.linear_v.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.23.self_attn_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.23.self_attn_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.3.conv_module.depthwise_conv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.3.conv_module.depthwise_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.3.conv_module.depthwise_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.3.conv_module.layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.3.conv_module.layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.3.conv_module.pointwise_conv1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.3.conv_module.pointwise_conv2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.3.ffn1.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.3.ffn1.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.3.ffn1.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.3.ffn1.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.3.ffn1_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.3.ffn1_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.3.ffn2.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.3.ffn2.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.3.ffn2.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.3.ffn2.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.3.ffn2_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.3.ffn2_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.3.final_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.3.final_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.3.self_attn.distance_embedding.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.3.self_attn.linear_k.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.3.self_attn.linear_k.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.3.self_attn.linear_out.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.3.self_attn.linear_out.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.3.self_attn.linear_q.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.3.self_attn.linear_q.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.3.self_attn.linear_v.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.3.self_attn.linear_v.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.3.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.3.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.4.conv_module.depthwise_conv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.4.conv_module.depthwise_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.4.conv_module.depthwise_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.4.conv_module.layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.4.conv_module.layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.4.conv_module.pointwise_conv1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.4.conv_module.pointwise_conv2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.4.ffn1.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.4.ffn1.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.4.ffn1.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.4.ffn1.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.4.ffn1_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.4.ffn1_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.4.ffn2.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.4.ffn2.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.4.ffn2.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.4.ffn2.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.4.ffn2_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.4.ffn2_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.4.final_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.4.final_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.4.self_attn.distance_embedding.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.4.self_attn.linear_k.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.4.self_attn.linear_k.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.4.self_attn.linear_out.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.4.self_attn.linear_out.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.4.self_attn.linear_q.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.4.self_attn.linear_q.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.4.self_attn.linear_v.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.4.self_attn.linear_v.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.4.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.4.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.5.conv_module.depthwise_conv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.5.conv_module.depthwise_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.5.conv_module.depthwise_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.5.conv_module.layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.5.conv_module.layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.5.conv_module.pointwise_conv1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.5.conv_module.pointwise_conv2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.5.ffn1.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.5.ffn1.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.5.ffn1.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.5.ffn1.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.5.ffn1_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.5.ffn1_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.5.ffn2.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.5.ffn2.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.5.ffn2.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.5.ffn2.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.5.ffn2_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.5.ffn2_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.5.final_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.5.final_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.5.self_attn.distance_embedding.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.5.self_attn.linear_k.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.5.self_attn.linear_k.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.5.self_attn.linear_out.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.5.self_attn.linear_out.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.5.self_attn.linear_q.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.5.self_attn.linear_q.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.5.self_attn.linear_v.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.5.self_attn.linear_v.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.5.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.5.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.6.conv_module.depthwise_conv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.6.conv_module.depthwise_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.6.conv_module.depthwise_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.6.conv_module.layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.6.conv_module.layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.6.conv_module.pointwise_conv1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.6.conv_module.pointwise_conv2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.6.ffn1.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.6.ffn1.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.6.ffn1.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.6.ffn1.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.6.ffn1_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.6.ffn1_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.6.ffn2.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.6.ffn2.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.6.ffn2.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.6.ffn2.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.6.ffn2_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.6.ffn2_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.6.final_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.6.final_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.6.self_attn.distance_embedding.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.6.self_attn.linear_k.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.6.self_attn.linear_k.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.6.self_attn.linear_out.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.6.self_attn.linear_out.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.6.self_attn.linear_q.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.6.self_attn.linear_q.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.6.self_attn.linear_v.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.6.self_attn.linear_v.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.6.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.6.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.7.conv_module.depthwise_conv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.7.conv_module.depthwise_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.7.conv_module.depthwise_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.7.conv_module.layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.7.conv_module.layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.7.conv_module.pointwise_conv1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.7.conv_module.pointwise_conv2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.7.ffn1.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.7.ffn1.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.7.ffn1.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.7.ffn1.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.7.ffn1_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.7.ffn1_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.7.ffn2.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.7.ffn2.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.7.ffn2.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.7.ffn2.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.7.ffn2_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.7.ffn2_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.7.final_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.7.final_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.7.self_attn.distance_embedding.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.7.self_attn.linear_k.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.7.self_attn.linear_k.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.7.self_attn.linear_out.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.7.self_attn.linear_out.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.7.self_attn.linear_q.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.7.self_attn.linear_q.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.7.self_attn.linear_v.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.7.self_attn.linear_v.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.7.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.7.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.8.conv_module.depthwise_conv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.8.conv_module.depthwise_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.8.conv_module.depthwise_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.8.conv_module.layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.8.conv_module.layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.8.conv_module.pointwise_conv1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.8.conv_module.pointwise_conv2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.8.ffn1.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.8.ffn1.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.8.ffn1.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.8.ffn1.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.8.ffn1_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.8.ffn1_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.8.ffn2.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.8.ffn2.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.8.ffn2.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.8.ffn2.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.8.ffn2_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.8.ffn2_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.8.final_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.8.final_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.8.self_attn.distance_embedding.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.8.self_attn.linear_k.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.8.self_attn.linear_k.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.8.self_attn.linear_out.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.8.self_attn.linear_out.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.8.self_attn.linear_q.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.8.self_attn.linear_q.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.8.self_attn.linear_v.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.8.self_attn.linear_v.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.8.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.8.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.9.conv_module.depthwise_conv.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.9.conv_module.depthwise_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.9.conv_module.depthwise_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.9.conv_module.layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.9.conv_module.layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.9.conv_module.pointwise_conv1.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.9.conv_module.pointwise_conv2.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.9.ffn1.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.9.ffn1.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.9.ffn1.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.9.ffn1.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.9.ffn1_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.9.ffn1_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.9.ffn2.intermediate_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.9.ffn2.intermediate_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.9.ffn2.output_dense.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.9.ffn2.output_dense.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.9.ffn2_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.9.ffn2_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.9.final_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.9.final_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.9.self_attn.distance_embedding.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.9.self_attn.linear_k.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.9.self_attn.linear_k.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.9.self_attn.linear_out.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.9.self_attn.linear_out.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.9.self_attn.linear_q.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.9.self_attn.linear_q.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.9.self_attn.linear_v.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.9.self_attn.linear_v.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.9.self_attn_layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.encoder.layers.9.self_attn_layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.feature_projection.layer_norm.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.feature_projection.layer_norm.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.feature_projection.projection.bias": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.feature_projection.projection.weight": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.w2vbert.encoder.masked_spec_embed": "model-00004-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.conv1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.conv1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.conv2.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.conv2.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.embed_positions.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.0.fc1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.0.fc1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.0.fc2.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.0.fc2.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.0.final_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.0.final_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.0.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.0.self_attn.out_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.0.self_attn.out_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.0.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.0.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.0.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.0.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.0.self_attn_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.0.self_attn_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.1.fc1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.1.fc1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.1.fc2.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.1.fc2.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.1.final_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.1.final_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.1.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.1.self_attn.out_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.1.self_attn.out_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.1.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.1.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.1.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.1.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.1.self_attn_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.1.self_attn_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.10.fc1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.10.fc1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.10.fc2.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.10.fc2.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.10.final_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.10.final_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.10.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.10.self_attn.out_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.10.self_attn.out_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.10.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.10.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.10.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.10.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.10.self_attn_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.10.self_attn_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.11.fc1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.11.fc1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.11.fc2.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.11.fc2.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.11.final_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.11.final_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.11.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.11.self_attn.out_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.11.self_attn.out_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.11.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.11.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.11.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.11.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.11.self_attn_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.11.self_attn_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.12.fc1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.12.fc1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.12.fc2.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.12.fc2.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.12.final_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.12.final_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.12.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.12.self_attn.out_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.12.self_attn.out_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.12.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.12.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.12.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.12.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.12.self_attn_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.12.self_attn_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.13.fc1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.13.fc1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.13.fc2.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.13.fc2.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.13.final_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.13.final_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.13.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.13.self_attn.out_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.13.self_attn.out_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.13.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.13.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.13.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.13.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.13.self_attn_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.13.self_attn_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.14.fc1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.14.fc1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.14.fc2.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.14.fc2.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.14.final_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.14.final_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.14.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.14.self_attn.out_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.14.self_attn.out_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.14.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.14.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.14.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.14.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.14.self_attn_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.14.self_attn_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.15.fc1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.15.fc1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.15.fc2.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.15.fc2.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.15.final_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.15.final_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.15.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.15.self_attn.out_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.15.self_attn.out_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.15.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.15.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.15.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.15.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.15.self_attn_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.15.self_attn_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.16.fc1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.16.fc1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.16.fc2.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.16.fc2.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.16.final_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.16.final_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.16.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.16.self_attn.out_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.16.self_attn.out_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.16.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.16.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.16.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.16.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.16.self_attn_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.16.self_attn_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.17.fc1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.17.fc1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.17.fc2.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.17.fc2.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.17.final_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.17.final_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.17.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.17.self_attn.out_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.17.self_attn.out_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.17.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.17.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.17.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.17.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.17.self_attn_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.17.self_attn_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.18.fc1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.18.fc1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.18.fc2.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.18.fc2.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.18.final_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.18.final_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.18.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.18.self_attn.out_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.18.self_attn.out_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.18.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.18.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.18.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.18.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.18.self_attn_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.18.self_attn_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.19.fc1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.19.fc1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.19.fc2.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.19.fc2.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.19.final_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.19.final_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.19.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.19.self_attn.out_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.19.self_attn.out_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.19.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.19.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.19.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.19.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.19.self_attn_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.19.self_attn_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.2.fc1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.2.fc1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.2.fc2.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.2.fc2.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.2.final_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.2.final_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.2.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.2.self_attn.out_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.2.self_attn.out_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.2.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.2.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.2.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.2.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.2.self_attn_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.2.self_attn_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.20.fc1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.20.fc1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.20.fc2.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.20.fc2.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.20.final_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.20.final_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.20.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.20.self_attn.out_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.20.self_attn.out_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.20.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.20.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.20.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.20.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.20.self_attn_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.20.self_attn_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.21.fc1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.21.fc1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.21.fc2.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.21.fc2.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.21.final_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.21.final_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.21.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.21.self_attn.out_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.21.self_attn.out_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.21.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.21.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.21.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.21.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.21.self_attn_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.21.self_attn_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.22.fc1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.22.fc1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.22.fc2.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.22.fc2.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.22.final_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.22.final_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.22.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.22.self_attn.out_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.22.self_attn.out_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.22.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.22.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.22.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.22.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.22.self_attn_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.22.self_attn_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.23.fc1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.23.fc1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.23.fc2.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.23.fc2.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.23.final_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.23.final_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.23.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.23.self_attn.out_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.23.self_attn.out_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.23.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.23.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.23.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.23.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.23.self_attn_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.23.self_attn_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.24.fc1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.24.fc1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.24.fc2.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.24.fc2.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.24.final_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.24.final_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.24.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.24.self_attn.out_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.24.self_attn.out_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.24.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.24.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.24.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.24.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.24.self_attn_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.24.self_attn_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.25.fc1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.25.fc1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.25.fc2.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.25.fc2.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.25.final_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.25.final_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.25.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.25.self_attn.out_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.25.self_attn.out_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.25.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.25.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.25.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.25.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.25.self_attn_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.25.self_attn_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.26.fc1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.26.fc1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.26.fc2.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.26.fc2.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.26.final_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.26.final_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.26.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.26.self_attn.out_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.26.self_attn.out_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.26.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.26.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.26.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.26.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.26.self_attn_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.26.self_attn_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.27.fc1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.27.fc1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.27.fc2.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.27.fc2.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.27.final_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.27.final_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.27.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.27.self_attn.out_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.27.self_attn.out_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.27.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.27.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.27.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.27.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.27.self_attn_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.27.self_attn_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.28.fc1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.28.fc1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.28.fc2.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.28.fc2.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.28.final_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.28.final_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.28.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.28.self_attn.out_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.28.self_attn.out_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.28.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.28.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.28.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.28.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.28.self_attn_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.28.self_attn_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.29.fc1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.29.fc1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.29.fc2.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.29.fc2.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.29.final_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.29.final_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.29.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.29.self_attn.out_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.29.self_attn.out_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.29.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.29.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.29.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.29.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.29.self_attn_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.29.self_attn_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.3.fc1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.3.fc1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.3.fc2.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.3.fc2.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.3.final_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.3.final_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.3.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.3.self_attn.out_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.3.self_attn.out_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.3.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.3.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.3.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.3.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.3.self_attn_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.3.self_attn_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.30.fc1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.30.fc1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.30.fc2.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.30.fc2.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.30.final_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.30.final_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.30.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.30.self_attn.out_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.30.self_attn.out_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.30.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.30.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.30.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.30.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.30.self_attn_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.30.self_attn_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.31.fc1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.31.fc1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.31.fc2.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.31.fc2.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.31.final_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.31.final_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.31.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.31.self_attn.out_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.31.self_attn.out_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.31.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.31.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.31.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.31.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.31.self_attn_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.31.self_attn_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.4.fc1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.4.fc1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.4.fc2.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.4.fc2.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.4.final_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.4.final_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.4.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.4.self_attn.out_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.4.self_attn.out_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.4.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.4.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.4.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.4.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.4.self_attn_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.4.self_attn_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.5.fc1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.5.fc1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.5.fc2.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.5.fc2.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.5.final_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.5.final_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.5.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.5.self_attn.out_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.5.self_attn.out_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.5.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.5.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.5.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.5.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.5.self_attn_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.5.self_attn_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.6.fc1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.6.fc1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.6.fc2.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.6.fc2.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.6.final_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.6.final_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.6.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.6.self_attn.out_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.6.self_attn.out_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.6.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.6.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.6.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.6.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.6.self_attn_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.6.self_attn_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.7.fc1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.7.fc1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.7.fc2.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.7.fc2.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.7.final_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.7.final_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.7.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.7.self_attn.out_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.7.self_attn.out_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.7.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.7.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.7.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.7.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.7.self_attn_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.7.self_attn_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.8.fc1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.8.fc1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.8.fc2.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.8.fc2.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.8.final_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.8.final_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.8.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.8.self_attn.out_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.8.self_attn.out_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.8.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.8.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.8.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.8.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.8.self_attn_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.8.self_attn_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.9.fc1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.9.fc1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.9.fc2.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.9.fc2.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.9.final_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.9.final_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.9.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.9.self_attn.out_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.9.self_attn.out_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.9.self_attn.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.9.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.9.self_attn.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.9.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.9.self_attn_layer_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_encoder.encoders.whisper.encoder.layers.9.self_attn_layer_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_end_emb": "model-00001-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.cond_end_emb": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.cond_start_emb": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.out_proj.muq.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.out_proj.muq.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.out_proj.sslam.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.out_proj.sslam.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.out_proj.w2vbert.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.out_proj.w2vbert.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.cross_attn_1.0.module.attention.k_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.cross_attn_1.0.module.attention.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.cross_attn_1.0.module.attention.o_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.cross_attn_1.0.module.attention.o_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.cross_attn_1.0.module.attention.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.cross_attn_1.0.module.attention.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.cross_attn_1.0.module.attention.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.cross_attn_1.0.module.attention.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.cross_attn_1.0.module.kv_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.cross_attn_1.0.module.kv_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.cross_attn_1.0.module.q_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.cross_attn_1.0.module.q_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.cross_attn_1.1.module.0.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.cross_attn_1.1.module.0.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.cross_attn_1.1.module.1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.cross_attn_1.1.module.1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.cross_attn_1.1.module.3.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.cross_attn_1.1.module.3.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.latent_provider._query": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.0.0.module.attention.k_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.0.0.module.attention.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.0.0.module.attention.o_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.0.0.module.attention.o_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.0.0.module.attention.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.0.0.module.attention.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.0.0.module.attention.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.0.0.module.attention.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.0.0.module.norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.0.0.module.norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.0.1.module.0.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.0.1.module.0.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.0.1.module.1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.0.1.module.1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.0.1.module.3.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.0.1.module.3.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.1.0.module.attention.k_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.1.0.module.attention.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.1.0.module.attention.o_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.1.0.module.attention.o_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.1.0.module.attention.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.1.0.module.attention.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.1.0.module.attention.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.1.0.module.attention.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.1.0.module.norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.1.0.module.norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.1.1.module.0.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.1.1.module.0.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.1.1.module.1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.1.1.module.1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.1.1.module.3.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.1.1.module.3.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.2.0.module.attention.k_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.2.0.module.attention.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.2.0.module.attention.o_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.2.0.module.attention.o_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.2.0.module.attention.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.2.0.module.attention.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.2.0.module.attention.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.2.0.module.attention.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.2.0.module.norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.2.0.module.norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.2.1.module.0.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.2.1.module.0.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.2.1.module.1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.2.1.module.1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.2.1.module.3.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.2.1.module.3.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.3.0.module.attention.k_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.3.0.module.attention.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.3.0.module.attention.o_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.3.0.module.attention.o_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.3.0.module.attention.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.3.0.module.attention.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.3.0.module.attention.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.3.0.module.attention.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.3.0.module.norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.3.0.module.norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.3.1.module.0.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.3.1.module.0.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.3.1.module.1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.3.1.module.1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.3.1.module.3.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.3.1.module.3.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.4.0.module.attention.k_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.4.0.module.attention.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.4.0.module.attention.o_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.4.0.module.attention.o_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.4.0.module.attention.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.4.0.module.attention.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.4.0.module.attention.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.4.0.module.attention.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.4.0.module.norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.4.0.module.norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.4.1.module.0.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.4.1.module.0.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.4.1.module.1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.4.1.module.1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.4.1.module.3.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.4.1.module.3.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.5.0.module.attention.k_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.5.0.module.attention.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.5.0.module.attention.o_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.5.0.module.attention.o_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.5.0.module.attention.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.5.0.module.attention.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.5.0.module.attention.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.5.0.module.attention.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.5.0.module.norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.5.0.module.norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.5.1.module.0.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.5.1.module.0.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.5.1.module.1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.5.1.module.1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.5.1.module.3.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.muq.self_attn_1.5.1.module.3.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.cross_attn_1.0.module.attention.k_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.cross_attn_1.0.module.attention.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.cross_attn_1.0.module.attention.o_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.cross_attn_1.0.module.attention.o_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.cross_attn_1.0.module.attention.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.cross_attn_1.0.module.attention.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.cross_attn_1.0.module.attention.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.cross_attn_1.0.module.attention.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.cross_attn_1.0.module.kv_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.cross_attn_1.0.module.kv_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.cross_attn_1.0.module.q_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.cross_attn_1.0.module.q_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.cross_attn_1.1.module.0.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.cross_attn_1.1.module.0.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.cross_attn_1.1.module.1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.cross_attn_1.1.module.1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.cross_attn_1.1.module.3.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.cross_attn_1.1.module.3.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.latent_provider._query": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.0.0.module.attention.k_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.0.0.module.attention.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.0.0.module.attention.o_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.0.0.module.attention.o_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.0.0.module.attention.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.0.0.module.attention.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.0.0.module.attention.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.0.0.module.attention.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.0.0.module.norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.0.0.module.norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.0.1.module.0.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.0.1.module.0.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.0.1.module.1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.0.1.module.1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.0.1.module.3.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.0.1.module.3.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.1.0.module.attention.k_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.1.0.module.attention.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.1.0.module.attention.o_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.1.0.module.attention.o_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.1.0.module.attention.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.1.0.module.attention.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.1.0.module.attention.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.1.0.module.attention.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.1.0.module.norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.1.0.module.norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.1.1.module.0.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.1.1.module.0.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.1.1.module.1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.1.1.module.1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.1.1.module.3.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.1.1.module.3.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.2.0.module.attention.k_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.2.0.module.attention.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.2.0.module.attention.o_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.2.0.module.attention.o_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.2.0.module.attention.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.2.0.module.attention.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.2.0.module.attention.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.2.0.module.attention.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.2.0.module.norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.2.0.module.norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.2.1.module.0.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.2.1.module.0.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.2.1.module.1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.2.1.module.1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.2.1.module.3.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.2.1.module.3.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.3.0.module.attention.k_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.3.0.module.attention.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.3.0.module.attention.o_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.3.0.module.attention.o_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.3.0.module.attention.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.3.0.module.attention.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.3.0.module.attention.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.3.0.module.attention.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.3.0.module.norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.3.0.module.norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.3.1.module.0.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.3.1.module.0.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.3.1.module.1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.3.1.module.1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.3.1.module.3.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.3.1.module.3.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.4.0.module.attention.k_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.4.0.module.attention.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.4.0.module.attention.o_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.4.0.module.attention.o_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.4.0.module.attention.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.4.0.module.attention.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.4.0.module.attention.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.4.0.module.attention.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.4.0.module.norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.4.0.module.norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.4.1.module.0.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.4.1.module.0.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.4.1.module.1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.4.1.module.1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.4.1.module.3.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.4.1.module.3.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.5.0.module.attention.k_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.5.0.module.attention.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.5.0.module.attention.o_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.5.0.module.attention.o_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.5.0.module.attention.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.5.0.module.attention.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.5.0.module.attention.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.5.0.module.attention.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.5.0.module.norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.5.0.module.norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.5.1.module.0.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.5.1.module.0.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.5.1.module.1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.5.1.module.1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.5.1.module.3.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.sslam.self_attn_1.5.1.module.3.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.cross_attn_1.0.module.attention.k_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.cross_attn_1.0.module.attention.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.cross_attn_1.0.module.attention.o_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.cross_attn_1.0.module.attention.o_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.cross_attn_1.0.module.attention.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.cross_attn_1.0.module.attention.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.cross_attn_1.0.module.attention.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.cross_attn_1.0.module.attention.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.cross_attn_1.0.module.kv_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.cross_attn_1.0.module.kv_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.cross_attn_1.0.module.q_norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.cross_attn_1.0.module.q_norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.cross_attn_1.1.module.0.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.cross_attn_1.1.module.0.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.cross_attn_1.1.module.1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.cross_attn_1.1.module.1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.cross_attn_1.1.module.3.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.cross_attn_1.1.module.3.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.latent_provider._query": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.0.0.module.attention.k_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.0.0.module.attention.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.0.0.module.attention.o_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.0.0.module.attention.o_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.0.0.module.attention.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.0.0.module.attention.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.0.0.module.attention.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.0.0.module.attention.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.0.0.module.norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.0.0.module.norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.0.1.module.0.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.0.1.module.0.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.0.1.module.1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.0.1.module.1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.0.1.module.3.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.0.1.module.3.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.1.0.module.attention.k_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.1.0.module.attention.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.1.0.module.attention.o_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.1.0.module.attention.o_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.1.0.module.attention.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.1.0.module.attention.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.1.0.module.attention.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.1.0.module.attention.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.1.0.module.norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.1.0.module.norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.1.1.module.0.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.1.1.module.0.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.1.1.module.1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.1.1.module.1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.1.1.module.3.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.1.1.module.3.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.2.0.module.attention.k_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.2.0.module.attention.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.2.0.module.attention.o_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.2.0.module.attention.o_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.2.0.module.attention.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.2.0.module.attention.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.2.0.module.attention.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.2.0.module.attention.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.2.0.module.norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.2.0.module.norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.2.1.module.0.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.2.1.module.0.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.2.1.module.1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.2.1.module.1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.2.1.module.3.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.2.1.module.3.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.3.0.module.attention.k_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.3.0.module.attention.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.3.0.module.attention.o_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.3.0.module.attention.o_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.3.0.module.attention.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.3.0.module.attention.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.3.0.module.attention.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.3.0.module.attention.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.3.0.module.norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.3.0.module.norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.3.1.module.0.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.3.1.module.0.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.3.1.module.1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.3.1.module.1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.3.1.module.3.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.3.1.module.3.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.4.0.module.attention.k_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.4.0.module.attention.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.4.0.module.attention.o_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.4.0.module.attention.o_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.4.0.module.attention.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.4.0.module.attention.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.4.0.module.attention.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.4.0.module.attention.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.4.0.module.norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.4.0.module.norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.4.1.module.0.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.4.1.module.0.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.4.1.module.1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.4.1.module.1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.4.1.module.3.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.4.1.module.3.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.5.0.module.attention.k_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.5.0.module.attention.k_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.5.0.module.attention.o_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.5.0.module.attention.o_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.5.0.module.attention.q_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.5.0.module.attention.q_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.5.0.module.attention.v_proj.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.5.0.module.attention.v_proj.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.5.0.module.norm.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.5.0.module.norm.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.5.1.module.0.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.5.1.module.0.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.5.1.module.1.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.5.1.module.1.weight": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.5.1.module.3.bias": "model-00005-of-00005.safetensors", |
| "model.audio_fusion.fusion_model.perceiver.w2vbert.self_attn_1.5.1.module.3.weight": "model-00005-of-00005.safetensors", |
| "model.audio_start_emb": "model-00001-of-00005.safetensors", |
| "model.embed_tokens.weight": "model-00001-of-00005.safetensors", |
| "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors", |
| "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", |
| "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00005.safetensors", |
| "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00005.safetensors", |
| "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors", |
| "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", |
| "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00005.safetensors", |
| "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00005.safetensors", |
| "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.16.mlp.down_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.16.mlp.up_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.17.input_layernorm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.17.mlp.down_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.17.mlp.up_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.18.input_layernorm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.18.mlp.down_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.18.mlp.up_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.19.input_layernorm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.19.mlp.down_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.19.mlp.up_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors", |
| "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", |
| "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00005.safetensors", |
| "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00005.safetensors", |
| "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.20.mlp.up_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.21.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.21.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.22.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.22.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.27.mlp.down_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.28.input_layernorm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.28.mlp.down_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.28.mlp.up_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.29.input_layernorm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.29.mlp.down_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.29.mlp.up_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors", |
| "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", |
| "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00005.safetensors", |
| "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00005.safetensors", |
| "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.30.input_layernorm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.30.mlp.down_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.30.mlp.up_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.31.input_layernorm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.31.mlp.down_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.31.mlp.up_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.32.input_layernorm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.32.mlp.down_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.32.mlp.up_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00005.safetensors", |
| "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors", |
| "model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors", |
| "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", |
| "model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors", |
| "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", |
| "model.layers.33.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", |
| "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", |
| "model.layers.33.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", |
| "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", |
| "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", |
| "model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors", |
| "model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors", |
| "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", |
| "model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors", |
| "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", |
| "model.layers.34.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", |
| "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", |
| "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", |
| "model.layers.34.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", |
| "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", |
| "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", |
| "model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors", |
| "model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors", |
| "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", |
| "model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors", |
| "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", |
| "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00005.safetensors", |
| "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", |
| "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", |
| "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00005.safetensors", |
| "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", |
| "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", |
| "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors", |
| "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", |
| "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00005.safetensors", |
| "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00005.safetensors", |
| "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors", |
| "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", |
| "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00005.safetensors", |
| "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00005.safetensors", |
| "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors", |
| "model.layers.6.mlp.down_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.6.mlp.up_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", |
| "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00005.safetensors", |
| "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00005.safetensors", |
| "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.7.input_layernorm.weight": "model-00001-of-00005.safetensors", |
| "model.layers.7.mlp.down_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.7.mlp.up_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", |
| "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00005.safetensors", |
| "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00005.safetensors", |
| "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00005.safetensors", |
| "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00005.safetensors", |
| "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", |
| "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00005.safetensors", |
| "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", |
| "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", |
| "model.norm.weight": "model-00004-of-00005.safetensors" |
| } |
| } |
|
|
