| { |
| "metadata": { |
| "total_size": 10347151840 |
| }, |
| "weight_map": { |
| "language_model.model.embed_tokens.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00003.safetensors", |
| "language_model.model.layers.17.mlp.down_proj.weight": "model-00003-of-00003.safetensors", |
| "language_model.model.layers.17.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", |
| "language_model.model.layers.17.mlp.up_proj.weight": "model-00003-of-00003.safetensors", |
| "language_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", |
| "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.17.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", |
| "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", |
| "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", |
| "language_model.model.norm.weight": "model-00003-of-00003.safetensors", |
| "multi_modal_projector.linear.bias": "model-00001-of-00003.safetensors", |
| "multi_modal_projector.linear.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.embeddings.norm.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.embeddings.norm.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.embeddings.patch_embeddings.projection.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.embeddings.patch_embeddings.projection.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.blocks.0.attention.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.blocks.0.attention.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.blocks.0.attention.self.key.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.blocks.0.attention.self.key.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.blocks.0.attention.self.query.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.blocks.0.attention.self.query.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.blocks.0.attention.self.relative_position_bias_table": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.blocks.0.attention.self.relative_position_index": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.blocks.0.attention.self.value.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.blocks.0.attention.self.value.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.blocks.0.intermediate.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.blocks.0.intermediate.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.blocks.0.layernorm_after.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.blocks.0.layernorm_after.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.blocks.0.layernorm_before.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.blocks.0.layernorm_before.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.blocks.0.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.blocks.0.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.blocks.1.attention.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.blocks.1.attention.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.blocks.1.attention.self.key.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.blocks.1.attention.self.key.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.blocks.1.attention.self.query.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.blocks.1.attention.self.query.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.blocks.1.attention.self.relative_position_bias_table": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.blocks.1.attention.self.relative_position_index": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.blocks.1.attention.self.value.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.blocks.1.attention.self.value.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.blocks.1.intermediate.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.blocks.1.intermediate.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.blocks.1.layernorm_after.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.blocks.1.layernorm_after.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.blocks.1.layernorm_before.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.blocks.1.layernorm_before.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.blocks.1.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.blocks.1.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.downsample.norm.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.downsample.norm.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.0.downsample.reduction.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.blocks.0.attention.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.blocks.0.attention.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.blocks.0.attention.self.key.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.blocks.0.attention.self.key.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.blocks.0.attention.self.query.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.blocks.0.attention.self.query.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.blocks.0.attention.self.relative_position_bias_table": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.blocks.0.attention.self.relative_position_index": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.blocks.0.attention.self.value.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.blocks.0.attention.self.value.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.blocks.0.intermediate.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.blocks.0.intermediate.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.blocks.0.layernorm_after.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.blocks.0.layernorm_after.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.blocks.0.layernorm_before.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.blocks.0.layernorm_before.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.blocks.0.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.blocks.0.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.blocks.1.attention.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.blocks.1.attention.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.blocks.1.attention.self.key.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.blocks.1.attention.self.key.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.blocks.1.attention.self.query.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.blocks.1.attention.self.query.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.blocks.1.attention.self.relative_position_bias_table": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.blocks.1.attention.self.relative_position_index": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.blocks.1.attention.self.value.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.blocks.1.attention.self.value.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.blocks.1.intermediate.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.blocks.1.intermediate.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.blocks.1.layernorm_after.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.blocks.1.layernorm_after.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.blocks.1.layernorm_before.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.blocks.1.layernorm_before.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.blocks.1.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.blocks.1.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.downsample.norm.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.downsample.norm.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.1.downsample.reduction.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.0.attention.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.0.attention.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.0.attention.self.key.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.0.attention.self.key.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.0.attention.self.query.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.0.attention.self.query.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.0.attention.self.relative_position_bias_table": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.0.attention.self.relative_position_index": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.0.attention.self.value.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.0.attention.self.value.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.0.intermediate.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.0.intermediate.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.0.layernorm_after.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.0.layernorm_after.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.0.layernorm_before.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.0.layernorm_before.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.0.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.0.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.1.attention.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.1.attention.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.1.attention.self.key.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.1.attention.self.key.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.1.attention.self.query.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.1.attention.self.query.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.1.attention.self.relative_position_bias_table": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.1.attention.self.relative_position_index": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.1.attention.self.value.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.1.attention.self.value.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.1.intermediate.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.1.intermediate.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.1.layernorm_after.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.1.layernorm_after.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.1.layernorm_before.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.1.layernorm_before.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.1.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.1.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.10.attention.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.10.attention.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.10.attention.self.key.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.10.attention.self.key.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.10.attention.self.query.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.10.attention.self.query.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.10.attention.self.relative_position_bias_table": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.10.attention.self.relative_position_index": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.10.attention.self.value.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.10.attention.self.value.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.10.intermediate.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.10.intermediate.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.10.layernorm_after.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.10.layernorm_after.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.10.layernorm_before.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.10.layernorm_before.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.10.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.10.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.11.attention.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.11.attention.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.11.attention.self.key.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.11.attention.self.key.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.11.attention.self.query.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.11.attention.self.query.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.11.attention.self.relative_position_bias_table": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.11.attention.self.relative_position_index": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.11.attention.self.value.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.11.attention.self.value.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.11.intermediate.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.11.intermediate.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.11.layernorm_after.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.11.layernorm_after.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.11.layernorm_before.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.11.layernorm_before.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.11.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.11.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.12.attention.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.12.attention.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.12.attention.self.key.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.12.attention.self.key.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.12.attention.self.query.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.12.attention.self.query.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.12.attention.self.relative_position_bias_table": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.12.attention.self.relative_position_index": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.12.attention.self.value.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.12.attention.self.value.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.12.intermediate.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.12.intermediate.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.12.layernorm_after.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.12.layernorm_after.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.12.layernorm_before.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.12.layernorm_before.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.12.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.12.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.13.attention.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.13.attention.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.13.attention.self.key.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.13.attention.self.key.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.13.attention.self.query.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.13.attention.self.query.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.13.attention.self.relative_position_bias_table": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.13.attention.self.relative_position_index": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.13.attention.self.value.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.13.attention.self.value.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.13.intermediate.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.13.intermediate.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.13.layernorm_after.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.13.layernorm_after.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.13.layernorm_before.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.13.layernorm_before.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.13.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.13.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.2.attention.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.2.attention.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.2.attention.self.key.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.2.attention.self.key.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.2.attention.self.query.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.2.attention.self.query.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.2.attention.self.relative_position_bias_table": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.2.attention.self.relative_position_index": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.2.attention.self.value.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.2.attention.self.value.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.2.intermediate.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.2.intermediate.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.2.layernorm_after.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.2.layernorm_after.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.2.layernorm_before.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.2.layernorm_before.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.2.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.2.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.3.attention.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.3.attention.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.3.attention.self.key.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.3.attention.self.key.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.3.attention.self.query.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.3.attention.self.query.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.3.attention.self.relative_position_bias_table": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.3.attention.self.relative_position_index": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.3.attention.self.value.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.3.attention.self.value.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.3.intermediate.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.3.intermediate.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.3.layernorm_after.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.3.layernorm_after.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.3.layernorm_before.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.3.layernorm_before.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.3.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.3.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.4.attention.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.4.attention.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.4.attention.self.key.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.4.attention.self.key.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.4.attention.self.query.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.4.attention.self.query.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.4.attention.self.relative_position_bias_table": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.4.attention.self.relative_position_index": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.4.attention.self.value.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.4.attention.self.value.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.4.intermediate.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.4.intermediate.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.4.layernorm_after.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.4.layernorm_after.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.4.layernorm_before.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.4.layernorm_before.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.4.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.4.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.5.attention.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.5.attention.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.5.attention.self.key.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.5.attention.self.key.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.5.attention.self.query.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.5.attention.self.query.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.5.attention.self.relative_position_bias_table": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.5.attention.self.relative_position_index": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.5.attention.self.value.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.5.attention.self.value.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.5.intermediate.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.5.intermediate.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.5.layernorm_after.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.5.layernorm_after.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.5.layernorm_before.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.5.layernorm_before.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.5.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.5.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.6.attention.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.6.attention.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.6.attention.self.key.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.6.attention.self.key.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.6.attention.self.query.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.6.attention.self.query.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.6.attention.self.relative_position_bias_table": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.6.attention.self.relative_position_index": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.6.attention.self.value.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.6.attention.self.value.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.6.intermediate.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.6.intermediate.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.6.layernorm_after.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.6.layernorm_after.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.6.layernorm_before.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.6.layernorm_before.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.6.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.6.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.7.attention.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.7.attention.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.7.attention.self.key.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.7.attention.self.key.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.7.attention.self.query.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.7.attention.self.query.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.7.attention.self.relative_position_bias_table": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.7.attention.self.relative_position_index": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.7.attention.self.value.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.7.attention.self.value.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.7.intermediate.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.7.intermediate.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.7.layernorm_after.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.7.layernorm_after.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.7.layernorm_before.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.7.layernorm_before.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.7.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.7.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.8.attention.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.8.attention.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.8.attention.self.key.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.8.attention.self.key.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.8.attention.self.query.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.8.attention.self.query.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.8.attention.self.relative_position_bias_table": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.8.attention.self.relative_position_index": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.8.attention.self.value.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.8.attention.self.value.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.8.intermediate.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.8.intermediate.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.8.layernorm_after.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.8.layernorm_after.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.8.layernorm_before.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.8.layernorm_before.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.8.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.8.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.9.attention.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.9.attention.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.9.attention.self.key.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.9.attention.self.key.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.9.attention.self.query.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.9.attention.self.query.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.9.attention.self.relative_position_bias_table": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.9.attention.self.relative_position_index": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.9.attention.self.value.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.9.attention.self.value.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.9.intermediate.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.9.intermediate.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.9.layernorm_after.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.9.layernorm_after.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.9.layernorm_before.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.9.layernorm_before.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.9.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.blocks.9.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.downsample.norm.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.downsample.norm.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.2.downsample.reduction.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.3.blocks.0.attention.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.3.blocks.0.attention.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.3.blocks.0.attention.self.key.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.3.blocks.0.attention.self.key.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.3.blocks.0.attention.self.query.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.3.blocks.0.attention.self.query.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.3.blocks.0.attention.self.relative_position_bias_table": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.3.blocks.0.attention.self.relative_position_index": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.3.blocks.0.attention.self.value.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.3.blocks.0.attention.self.value.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.3.blocks.0.intermediate.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.3.blocks.0.intermediate.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.3.blocks.0.layernorm_after.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.3.blocks.0.layernorm_after.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.3.blocks.0.layernorm_before.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.3.blocks.0.layernorm_before.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.3.blocks.0.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.3.blocks.0.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.3.blocks.1.attention.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.3.blocks.1.attention.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.3.blocks.1.attention.self.key.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.3.blocks.1.attention.self.key.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.3.blocks.1.attention.self.query.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.3.blocks.1.attention.self.query.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.3.blocks.1.attention.self.relative_position_bias_table": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.3.blocks.1.attention.self.relative_position_index": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.3.blocks.1.attention.self.value.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.3.blocks.1.attention.self.value.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.3.blocks.1.intermediate.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.3.blocks.1.intermediate.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.3.blocks.1.layernorm_after.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.3.blocks.1.layernorm_after.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.3.blocks.1.layernorm_before.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.3.blocks.1.layernorm_before.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.3.blocks.1.output.dense.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.encoder_model.encoder.layers.3.blocks.1.output.dense.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.pam.embedding_projection_layer.0.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.pam.embedding_projection_layer.0.weight": "model-00001-of-00003.safetensors", |
| "vision_tower.model.pam.embedding_projection_layer.1.bias": "model-00001-of-00003.safetensors", |
| "vision_tower.model.pam.embedding_projection_layer.1.weight": "model-00001-of-00003.safetensors" |
| } |
| } |
|
|
