| { |
| "activation_func": "swiglu", |
| "activation_func_fp8_input_store": false, |
| "add_bias_linear": false, |
| "architectures": [ |
| "ZayaForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bias_activation_fusion": true, |
| "bos_token_id": 2, |
| "cca": true, |
| "cca_time0": 2, |
| "cca_time1": 2, |
| "clamp_temp": false, |
| "dtype": "bfloat16", |
| "eos_token_id": 106, |
| "ffn_hidden_size": 4096, |
| "gated_linear_unit": true, |
| "head_dim": 128, |
| "hidden_size": 2048, |
| "kv_channels": 128, |
| "lm_head_bias": false, |
| "mamba_cache_dtype": "float32", |
| "max_position_embeddings": 131072, |
| "model_type": "zaya", |
| "moe_router_topk": 1, |
| "norm_epsilon": 1e-05, |
| "normalization": "RMSNorm", |
| "num_attention_heads": 8, |
| "num_experts": 16, |
| "num_hidden_layers": 80, |
| "num_key_value_heads": 2, |
| "num_query_groups": 2, |
| "pad_token_id": 0, |
| "partial_rotary_factor": 0.5, |
| "residual_in_fp32": true, |
| "rope_parameters": { |
| "partial_rotary_factor": 0.5, |
| "rope_theta": 5000000, |
| "rope_type": "default" |
| }, |
| "rope_theta": 5000000, |
| "scale_residual_merge": true, |
| "sliding_window": null, |
| "swa_layers": null, |
| "swa_rotary_base": null, |
| "transformers_version": "4.57.1", |
| "use_cache": false, |
| "vocab_size": 262272, |
| "zaya_high_prec": true, |
| "zaya_mlp_expansion": 256, |
| "zaya_use_eda": true, |
| "zaya_use_mod": true, |
| "quantization_config": { |
| "config_groups": { |
| "group_0": { |
| "input_activations": { |
| "dynamic": false, |
| "num_bits": 4, |
| "type": "float", |
| "group_size": 16 |
| }, |
| "weights": { |
| "dynamic": false, |
| "num_bits": 4, |
| "type": "float", |
| "group_size": 16 |
| }, |
| "targets": [ |
| "Linear" |
| ] |
| } |
| }, |
| "ignore": [ |
| "lm_head", |
| "model.layers.0.self_attn.qkv.conv_qk*", |
| "model.layers.1.zaya_block.router*", |
| "model.layers.10.self_attn.qkv.conv_qk*", |
| "model.layers.11.zaya_block.router*", |
| "model.layers.12.self_attn.qkv.conv_qk*", |
| "model.layers.13.zaya_block.router*", |
| "model.layers.14.self_attn.qkv.conv_qk*", |
| "model.layers.15.zaya_block.router*", |
| "model.layers.16.self_attn.qkv.conv_qk*", |
| "model.layers.17.zaya_block.router*", |
| "model.layers.18.self_attn.qkv.conv_qk*", |
| "model.layers.19.zaya_block.router*", |
| "model.layers.2.self_attn.qkv.conv_qk*", |
| "model.layers.20.self_attn.qkv.conv_qk*", |
| "model.layers.21.zaya_block.router*", |
| "model.layers.22.self_attn.qkv.conv_qk*", |
| "model.layers.23.zaya_block.router*", |
| "model.layers.24.self_attn.qkv.conv_qk*", |
| "model.layers.25.zaya_block.router*", |
| "model.layers.26.self_attn.qkv.conv_qk*", |
| "model.layers.27.zaya_block.router*", |
| "model.layers.28.self_attn.qkv.conv_qk*", |
| "model.layers.29.zaya_block.router*", |
| "model.layers.3.zaya_block.router*", |
| "model.layers.30.self_attn.qkv.conv_qk*", |
| "model.layers.31.zaya_block.router*", |
| "model.layers.32.self_attn.qkv.conv_qk*", |
| "model.layers.33.zaya_block.router*", |
| "model.layers.34.self_attn.qkv.conv_qk*", |
| "model.layers.35.zaya_block.router*", |
| "model.layers.36.self_attn.qkv.conv_qk*", |
| "model.layers.37.zaya_block.router*", |
| "model.layers.38.self_attn.qkv.conv_qk*", |
| "model.layers.39.zaya_block.router*", |
| "model.layers.4.self_attn.qkv.conv_qk*", |
| "model.layers.40.self_attn.qkv.conv_qk*", |
| "model.layers.41.zaya_block.router*", |
| "model.layers.42.self_attn.qkv.conv_qk*", |
| "model.layers.43.zaya_block.router*", |
| "model.layers.44.self_attn.qkv.conv_qk*", |
| "model.layers.45.zaya_block.router*", |
| "model.layers.46.self_attn.qkv.conv_qk*", |
| "model.layers.47.zaya_block.router*", |
| "model.layers.48.self_attn.qkv.conv_qk*", |
| "model.layers.49.zaya_block.router*", |
| "model.layers.5.zaya_block.router*", |
| "model.layers.50.self_attn.qkv.conv_qk*", |
| "model.layers.51.zaya_block.router*", |
| "model.layers.52.self_attn.qkv.conv_qk*", |
| "model.layers.53.zaya_block.router*", |
| "model.layers.54.self_attn.qkv.conv_qk*", |
| "model.layers.55.zaya_block.router*", |
| "model.layers.56.self_attn.qkv.conv_qk*", |
| "model.layers.57.zaya_block.router*", |
| "model.layers.58.self_attn.qkv.conv_qk*", |
| "model.layers.59.zaya_block.router*", |
| "model.layers.6.self_attn.qkv.conv_qk*", |
| "model.layers.60.self_attn.qkv.conv_qk*", |
| "model.layers.61.zaya_block.router*", |
| "model.layers.62.self_attn.qkv.conv_qk*", |
| "model.layers.63.zaya_block.router*", |
| "model.layers.64.self_attn.qkv.conv_qk*", |
| "model.layers.65.zaya_block.router*", |
| "model.layers.66.self_attn.qkv.conv_qk*", |
| "model.layers.67.zaya_block.router*", |
| "model.layers.68.self_attn.qkv.conv_qk*", |
| "model.layers.69.zaya_block.router*", |
| "model.layers.7.zaya_block.router*", |
| "model.layers.70.self_attn.qkv.conv_qk*", |
| "model.layers.71.zaya_block.router*", |
| "model.layers.72.self_attn.qkv.conv_qk*", |
| "model.layers.73.zaya_block.router*", |
| "model.layers.74.self_attn.qkv.conv_qk*", |
| "model.layers.75.zaya_block.router*", |
| "model.layers.76.self_attn.qkv.conv_qk*", |
| "model.layers.77.zaya_block.router*", |
| "model.layers.78.self_attn.qkv.conv_qk*", |
| "model.layers.79.zaya_block.router*", |
| "model.layers.8.self_attn.qkv.conv_qk*", |
| "model.layers.9.zaya_block.router*" |
| ], |
| "quant_algo": "NVFP4", |
| "producer": { |
| "name": "modelopt", |
| "version": "0.44.0" |
| }, |
| "quant_method": "modelopt" |
| } |
| } |