| { |
| "config_groups": { |
| "group_0": { |
| "targets": [ |
| "Linear" |
| ], |
| "weights": { |
| "num_bits": 4, |
| "type": "float", |
| "symmetric": true, |
| "group_size": 32, |
| "strategy": "group", |
| "block_structure": null, |
| "dynamic": false, |
| "actorder": null, |
| "scale_dtype": "torch.uint8", |
| "zp_dtype": null, |
| "observer": "memoryless_minmax", |
| "observer_kwargs": {} |
| }, |
| "input_activations": { |
| "num_bits": 4, |
| "type": "float", |
| "symmetric": true, |
| "group_size": 32, |
| "strategy": "group", |
| "block_structure": null, |
| "dynamic": true, |
| "actorder": null, |
| "scale_dtype": "torch.uint8", |
| "zp_dtype": null, |
| "observer": null, |
| "observer_kwargs": {} |
| }, |
| "output_activations": null, |
| "format": null |
| } |
| }, |
| "quant_method": "compressed-tensors", |
| "kv_cache_scheme": null, |
| "format": "mxfp4-pack-quantized", |
| "quantization_status": "compressed", |
| "global_compression_ratio": null, |
| "ignore": [ |
| "model.language_model.embed_tokens", |
| "model.language_model.layers.0.input_layernorm", |
| "model.language_model.layers.0.linear_attn.conv1d", |
| "model.language_model.layers.0.linear_attn.norm", |
| "model.language_model.layers.0.post_attention_layernorm", |
| "model.language_model.layers.1.input_layernorm", |
| "model.language_model.layers.1.linear_attn.conv1d", |
| "model.language_model.layers.1.linear_attn.norm", |
| "model.language_model.layers.1.post_attention_layernorm", |
| "model.language_model.layers.2.input_layernorm", |
| "model.language_model.layers.2.linear_attn.conv1d", |
| "model.language_model.layers.2.linear_attn.norm", |
| "model.language_model.layers.2.post_attention_layernorm", |
| "model.language_model.layers.3.input_layernorm", |
| "model.language_model.layers.3.post_attention_layernorm", |
| "model.language_model.layers.3.self_attn.k_norm", |
| "model.language_model.layers.3.self_attn.q_norm", |
| "model.language_model.layers.4.input_layernorm", |
| "model.language_model.layers.4.linear_attn.conv1d", |
| "model.visual.blocks.0.attn.proj", |
| "model.visual.blocks.0.attn.qkv", |
| "model.visual.blocks.0.mlp.linear_fc1", |
| "model.visual.blocks.0.mlp.linear_fc2", |
| "model.visual.blocks.0.norm1", |
| "model.visual.blocks.0.norm2", |
| "model.visual.blocks.1.attn.proj", |
| "model.visual.blocks.1.attn.qkv", |
| "model.visual.blocks.1.mlp.linear_fc1", |
| "model.visual.blocks.1.mlp.linear_fc2", |
| "model.visual.blocks.1.norm1", |
| "model.visual.blocks.1.norm2", |
| "model.visual.blocks.10.attn.proj", |
| "model.visual.blocks.10.attn.qkv", |
| "model.visual.blocks.10.mlp.linear_fc1", |
| "model.visual.blocks.10.mlp.linear_fc2", |
| "model.visual.blocks.10.norm1", |
| "model.visual.blocks.10.norm2", |
| "model.visual.blocks.11.attn.proj", |
| "model.visual.blocks.11.attn.qkv", |
| "model.visual.blocks.11.mlp.linear_fc1", |
| "model.visual.blocks.11.mlp.linear_fc2", |
| "model.visual.blocks.11.norm1", |
| "model.visual.blocks.11.norm2", |
| "model.visual.blocks.12.attn.proj", |
| "model.visual.blocks.12.attn.qkv", |
| "model.visual.blocks.12.mlp.linear_fc1", |
| "model.visual.blocks.12.mlp.linear_fc2", |
| "model.visual.blocks.12.norm1", |
| "model.visual.blocks.12.norm2", |
| "model.visual.blocks.13.attn.proj", |
| "model.visual.blocks.13.attn.qkv", |
| "model.visual.blocks.13.mlp.linear_fc1", |
| "model.visual.blocks.13.mlp.linear_fc2", |
| "model.visual.blocks.13.norm1", |
| "model.visual.blocks.13.norm2", |
| "model.visual.blocks.14.attn.proj", |
| "model.visual.blocks.14.attn.qkv", |
| "model.visual.blocks.14.mlp.linear_fc1", |
| "model.visual.blocks.14.mlp.linear_fc2", |
| "model.visual.blocks.14.norm1", |
| "model.visual.blocks.14.norm2", |
| "model.visual.blocks.15.attn.proj", |
| "model.visual.blocks.15.attn.qkv", |
| "model.visual.blocks.15.mlp.linear_fc1", |
| "model.visual.blocks.15.mlp.linear_fc2", |
| "model.visual.blocks.15.norm1", |
| "model.visual.blocks.15.norm2", |
| "model.visual.blocks.16.attn.proj", |
| "model.visual.blocks.16.attn.qkv", |
| "model.visual.blocks.16.mlp.linear_fc1", |
| "model.visual.blocks.16.mlp.linear_fc2", |
| "model.visual.blocks.16.norm1", |
| "model.visual.blocks.16.norm2", |
| "model.visual.blocks.17.attn.proj", |
| "model.visual.blocks.17.attn.qkv", |
| "model.visual.blocks.17.mlp.linear_fc1", |
| "model.visual.blocks.17.mlp.linear_fc2", |
| "model.visual.blocks.17.norm1", |
| "model.visual.blocks.17.norm2", |
| "model.visual.blocks.18.attn.proj", |
| "model.visual.blocks.18.attn.qkv", |
| "model.visual.blocks.18.mlp.linear_fc1", |
| "model.visual.blocks.18.mlp.linear_fc2", |
| "model.visual.blocks.18.norm1", |
| "model.visual.blocks.18.norm2", |
| "model.visual.blocks.19.attn.proj", |
| "model.visual.blocks.19.attn.qkv", |
| "model.visual.blocks.19.mlp.linear_fc1", |
| "model.visual.blocks.19.mlp.linear_fc2", |
| "model.visual.blocks.19.norm1", |
| "model.visual.blocks.19.norm2", |
| "model.visual.blocks.2.attn.proj", |
| "model.visual.blocks.2.attn.qkv", |
| "model.visual.blocks.2.mlp.linear_fc1", |
| "model.visual.blocks.2.mlp.linear_fc2", |
| "model.visual.blocks.2.norm1", |
| "model.visual.blocks.2.norm2", |
| "model.visual.blocks.20.attn.proj", |
| "model.visual.blocks.20.attn.qkv", |
| "model.visual.blocks.20.mlp.linear_fc1", |
| "model.visual.blocks.20.mlp.linear_fc2", |
| "model.visual.blocks.20.norm1", |
| "model.visual.blocks.20.norm2", |
| "model.visual.blocks.21.attn.proj", |
| "model.visual.blocks.21.attn.qkv", |
| "model.visual.blocks.21.mlp.linear_fc1", |
| "model.visual.blocks.21.mlp.linear_fc2", |
| "model.visual.blocks.21.norm1", |
| "model.visual.blocks.21.norm2", |
| "model.visual.blocks.22.attn.proj", |
| "model.visual.blocks.22.attn.qkv", |
| "model.visual.blocks.22.mlp.linear_fc1", |
| "model.visual.blocks.22.mlp.linear_fc2", |
| "model.visual.blocks.22.norm1", |
| "model.visual.blocks.22.norm2", |
| "model.visual.blocks.23.attn.proj", |
| "model.visual.blocks.23.attn.qkv", |
| "model.visual.blocks.23.mlp.linear_fc1", |
| "model.visual.blocks.23.mlp.linear_fc2", |
| "model.visual.blocks.23.norm1", |
| "model.visual.blocks.23.norm2", |
| "model.visual.blocks.24.attn.proj", |
| "model.visual.blocks.24.attn.qkv", |
| "model.visual.blocks.24.mlp.linear_fc1", |
| "model.visual.blocks.24.mlp.linear_fc2", |
| "model.visual.blocks.24.norm1", |
| "model.visual.blocks.24.norm2", |
| "model.visual.blocks.25.attn.proj", |
| "model.visual.blocks.25.attn.qkv", |
| "model.visual.blocks.25.mlp.linear_fc1", |
| "model.visual.blocks.25.mlp.linear_fc2", |
| "model.visual.blocks.25.norm1", |
| "model.visual.blocks.25.norm2", |
| "model.visual.blocks.26.attn.proj", |
| "model.visual.blocks.26.attn.qkv", |
| "model.visual.blocks.26.mlp.linear_fc1", |
| "model.visual.blocks.26.mlp.linear_fc2", |
| "model.visual.blocks.26.norm1", |
| "model.visual.blocks.26.norm2", |
| "model.visual.blocks.3.attn.proj", |
| "model.visual.blocks.3.attn.qkv", |
| "model.visual.blocks.3.mlp.linear_fc1", |
| "model.visual.blocks.3.mlp.linear_fc2", |
| "model.visual.blocks.3.norm1", |
| "model.visual.blocks.3.norm2", |
| "model.visual.blocks.4.attn.proj", |
| "model.visual.blocks.4.attn.qkv", |
| "model.visual.blocks.4.mlp.linear_fc1", |
| "model.visual.blocks.4.mlp.linear_fc2", |
| "model.visual.blocks.4.norm1", |
| "model.visual.blocks.4.norm2", |
| "model.visual.blocks.5.attn.proj", |
| "model.visual.blocks.5.attn.qkv", |
| "model.visual.blocks.5.mlp.linear_fc1", |
| "model.visual.blocks.5.mlp.linear_fc2", |
| "model.visual.blocks.5.norm1", |
| "model.visual.blocks.5.norm2", |
| "model.visual.blocks.6.attn.proj", |
| "model.visual.blocks.6.attn.qkv", |
| "model.visual.blocks.6.mlp.linear_fc1", |
| "model.visual.blocks.6.mlp.linear_fc2", |
| "model.visual.blocks.6.norm1", |
| "model.visual.blocks.6.norm2", |
| "model.visual.blocks.7.attn.proj", |
| "model.visual.blocks.7.attn.qkv", |
| "model.visual.blocks.7.mlp.linear_fc1", |
| "model.visual.blocks.7.mlp.linear_fc2", |
| "model.visual.blocks.7.norm1", |
| "model.visual.blocks.7.norm2", |
| "model.visual.blocks.8.attn.proj", |
| "model.visual.blocks.8.attn.qkv", |
| "model.visual.blocks.8.mlp.linear_fc1", |
| "model.visual.blocks.8.mlp.linear_fc2", |
| "model.visual.blocks.8.norm1", |
| "model.visual.blocks.8.norm2", |
| "model.visual.blocks.9.attn.proj", |
| "model.visual.blocks.9.attn.qkv", |
| "model.visual.blocks.9.mlp.linear_fc1", |
| "model.visual.blocks.9.mlp.linear_fc2", |
| "model.visual.blocks.9.norm1", |
| "model.visual.blocks.9.norm2", |
| "model.visual.merger.linear_fc1", |
| "model.visual.merger.linear_fc2", |
| "model.visual.merger.norm", |
| "model.visual.patch_embed.proj", |
| "model.visual.pos_embed", |
| "lm_head", |
| "mtp.fc", |
| "mtp.layers.0.input_layernorm", |
| "mtp.layers.0.mlp.down_proj", |
| "mtp.layers.0.mlp.gate_proj", |
| "mtp.layers.0.mlp.up_proj", |
| "mtp.layers.0.post_attention_layernorm", |
| "mtp.layers.0.self_attn.k_norm", |
| "mtp.layers.0.self_attn.k_proj", |
| "mtp.layers.0.self_attn.o_proj", |
| "mtp.layers.0.self_attn.q_norm", |
| "mtp.layers.0.self_attn.q_proj", |
| "mtp.layers.0.self_attn.v_proj", |
| "mtp.norm", |
| "mtp.pre_fc_norm_embedding", |
| "mtp.pre_fc_norm_hidden", |
| "model.language_model.layers.10.input_layernorm", |
| "model.language_model.layers.10.linear_attn.conv1d", |
| "model.language_model.layers.10.linear_attn.norm", |
| "model.language_model.layers.10.post_attention_layernorm", |
| "model.language_model.layers.11.input_layernorm", |
| "model.language_model.layers.11.post_attention_layernorm", |
| "model.language_model.layers.11.self_attn.k_norm", |
| "model.language_model.layers.11.self_attn.q_norm", |
| "model.language_model.layers.12.input_layernorm", |
| "model.language_model.layers.12.linear_attn.conv1d", |
| "model.language_model.layers.12.linear_attn.norm", |
| "model.language_model.layers.12.post_attention_layernorm", |
| "model.language_model.layers.13.input_layernorm", |
| "model.language_model.layers.13.linear_attn.conv1d", |
| "model.language_model.layers.13.linear_attn.norm", |
| "model.language_model.layers.13.post_attention_layernorm", |
| "model.language_model.layers.14.input_layernorm", |
| "model.language_model.layers.14.linear_attn.conv1d", |
| "model.language_model.layers.14.linear_attn.norm", |
| "model.language_model.layers.14.post_attention_layernorm", |
| "model.language_model.layers.15.post_attention_layernorm", |
| "model.language_model.layers.15.input_layernorm", |
| "model.language_model.layers.15.self_attn.k_norm", |
| "model.language_model.layers.15.self_attn.q_norm", |
| "model.language_model.layers.8.input_layernorm", |
| "model.language_model.layers.8.linear_attn.conv1d", |
| "model.language_model.layers.8.linear_attn.norm", |
| "model.language_model.layers.8.post_attention_layernorm", |
| "model.language_model.layers.9.input_layernorm", |
| "model.language_model.layers.9.linear_attn.conv1d", |
| "model.language_model.layers.9.linear_attn.norm", |
| "model.language_model.layers.9.post_attention_layernorm", |
| "model.language_model.layers.21.post_attention_layernorm", |
| "model.language_model.layers.22.input_layernorm", |
| "model.language_model.layers.22.linear_attn.conv1d", |
| "model.language_model.layers.22.linear_attn.norm", |
| "model.language_model.layers.22.post_attention_layernorm", |
| "model.language_model.layers.23.input_layernorm", |
| "model.language_model.layers.23.post_attention_layernorm", |
| "model.language_model.layers.23.self_attn.k_norm", |
| "model.language_model.layers.23.self_attn.q_norm", |
| "model.language_model.layers.16.input_layernorm", |
| "model.language_model.layers.16.linear_attn.conv1d", |
| "model.language_model.layers.16.linear_attn.norm", |
| "model.language_model.layers.16.post_attention_layernorm", |
| "model.language_model.layers.17.input_layernorm", |
| "model.language_model.layers.17.linear_attn.conv1d", |
| "model.language_model.layers.17.linear_attn.norm", |
| "model.language_model.layers.17.post_attention_layernorm", |
| "model.language_model.layers.18.input_layernorm", |
| "model.language_model.layers.18.linear_attn.conv1d", |
| "model.language_model.layers.18.linear_attn.norm", |
| "model.language_model.layers.18.post_attention_layernorm", |
| "model.language_model.layers.19.input_layernorm", |
| "model.language_model.layers.19.post_attention_layernorm", |
| "model.language_model.layers.19.self_attn.k_norm", |
| "model.language_model.layers.19.self_attn.q_norm", |
| "model.language_model.layers.20.input_layernorm", |
| "model.language_model.layers.20.linear_attn.conv1d", |
| "model.language_model.layers.20.linear_attn.norm", |
| "model.language_model.layers.20.post_attention_layernorm", |
| "model.language_model.layers.21.input_layernorm", |
| "model.language_model.layers.21.linear_attn.conv1d", |
| "model.language_model.layers.21.linear_attn.norm", |
| "model.language_model.layers.29.post_attention_layernorm", |
| "model.language_model.layers.30.input_layernorm", |
| "model.language_model.layers.30.linear_attn.conv1d", |
| "model.language_model.layers.30.linear_attn.norm", |
| "model.language_model.layers.30.post_attention_layernorm", |
| "model.language_model.layers.31.input_layernorm", |
| "model.language_model.layers.31.post_attention_layernorm", |
| "model.language_model.layers.31.self_attn.k_norm", |
| "model.language_model.layers.31.self_attn.q_norm", |
| "model.language_model.layers.24.input_layernorm", |
| "model.language_model.layers.24.linear_attn.conv1d", |
| "model.language_model.layers.24.linear_attn.norm", |
| "model.language_model.layers.24.post_attention_layernorm", |
| "model.language_model.layers.25.input_layernorm", |
| "model.language_model.layers.25.linear_attn.conv1d", |
| "model.language_model.layers.25.linear_attn.norm", |
| "model.language_model.layers.25.post_attention_layernorm", |
| "model.language_model.layers.26.input_layernorm", |
| "model.language_model.layers.26.linear_attn.conv1d", |
| "model.language_model.layers.26.linear_attn.norm", |
| "model.language_model.layers.26.post_attention_layernorm", |
| "model.language_model.layers.27.input_layernorm", |
| "model.language_model.layers.27.post_attention_layernorm", |
| "model.language_model.layers.27.self_attn.k_norm", |
| "model.language_model.layers.27.self_attn.q_norm", |
| "model.language_model.layers.28.input_layernorm", |
| "model.language_model.layers.28.linear_attn.conv1d", |
| "model.language_model.layers.28.linear_attn.norm", |
| "model.language_model.layers.28.post_attention_layernorm", |
| "model.language_model.layers.29.input_layernorm", |
| "model.language_model.layers.29.linear_attn.conv1d", |
| "model.language_model.layers.29.linear_attn.norm", |
| "model.language_model.layers.32.input_layernorm", |
| "model.language_model.layers.32.linear_attn.conv1d", |
| "model.language_model.layers.32.linear_attn.norm", |
| "model.language_model.layers.32.post_attention_layernorm", |
| "model.language_model.layers.33.input_layernorm", |
| "model.language_model.layers.33.linear_attn.conv1d", |
| "model.language_model.layers.33.linear_attn.norm", |
| "model.language_model.layers.33.post_attention_layernorm", |
| "model.language_model.layers.34.input_layernorm", |
| "model.language_model.layers.34.linear_attn.conv1d", |
| "model.language_model.layers.34.linear_attn.norm", |
| "model.language_model.layers.34.post_attention_layernorm", |
| "model.language_model.layers.35.input_layernorm", |
| "model.language_model.layers.35.post_attention_layernorm", |
| "model.language_model.layers.35.self_attn.k_norm", |
| "model.language_model.layers.35.self_attn.q_norm", |
| "model.language_model.layers.36.input_layernorm", |
| "model.language_model.layers.36.linear_attn.conv1d", |
| "model.language_model.layers.36.linear_attn.norm", |
| "model.language_model.layers.36.post_attention_layernorm", |
| "model.language_model.layers.37.input_layernorm", |
| "model.language_model.layers.37.linear_attn.conv1d", |
| "model.language_model.layers.37.linear_attn.norm", |
| "model.language_model.layers.37.post_attention_layernorm", |
| "model.language_model.layers.38.input_layernorm", |
| "model.language_model.layers.38.linear_attn.conv1d", |
| "model.language_model.layers.38.linear_attn.norm", |
| "model.language_model.layers.38.post_attention_layernorm", |
| "model.language_model.layers.39.input_layernorm", |
| "model.language_model.layers.39.post_attention_layernorm", |
| "model.language_model.layers.39.self_attn.k_norm", |
| "model.language_model.layers.39.self_attn.q_norm", |
| "model.language_model.layers.4.linear_attn.norm", |
| "model.language_model.layers.4.post_attention_layernorm", |
| "model.language_model.layers.5.input_layernorm", |
| "model.language_model.layers.5.linear_attn.conv1d", |
| "model.language_model.layers.5.linear_attn.norm", |
| "model.language_model.layers.5.post_attention_layernorm", |
| "model.language_model.layers.6.input_layernorm", |
| "model.language_model.layers.6.linear_attn.conv1d", |
| "model.language_model.layers.6.linear_attn.norm", |
| "model.language_model.layers.6.post_attention_layernorm", |
| "model.language_model.layers.7.input_layernorm", |
| "model.language_model.layers.7.post_attention_layernorm", |
| "model.language_model.layers.7.self_attn.k_norm", |
| "model.language_model.layers.7.self_attn.q_norm", |
| "model.language_model.layers.45.post_attention_layernorm", |
| "model.language_model.layers.46.input_layernorm", |
| "model.language_model.layers.46.linear_attn.conv1d", |
| "model.language_model.layers.46.linear_attn.norm", |
| "model.language_model.layers.46.post_attention_layernorm", |
| "model.language_model.layers.47.input_layernorm", |
| "model.language_model.layers.47.post_attention_layernorm", |
| "model.language_model.layers.47.self_attn.k_norm", |
| "model.language_model.layers.47.self_attn.q_norm", |
| "model.language_model.layers.40.input_layernorm", |
| "model.language_model.layers.40.linear_attn.conv1d", |
| "model.language_model.layers.40.linear_attn.norm", |
| "model.language_model.layers.40.post_attention_layernorm", |
| "model.language_model.layers.41.input_layernorm", |
| "model.language_model.layers.41.linear_attn.conv1d", |
| "model.language_model.layers.41.linear_attn.norm", |
| "model.language_model.layers.41.post_attention_layernorm", |
| "model.language_model.layers.42.input_layernorm", |
| "model.language_model.layers.42.linear_attn.conv1d", |
| "model.language_model.layers.42.linear_attn.norm", |
| "model.language_model.layers.42.post_attention_layernorm", |
| "model.language_model.layers.43.input_layernorm", |
| "model.language_model.layers.43.post_attention_layernorm", |
| "model.language_model.layers.43.self_attn.k_norm", |
| "model.language_model.layers.43.self_attn.q_norm", |
| "model.language_model.layers.44.input_layernorm", |
| "model.language_model.layers.44.linear_attn.conv1d", |
| "model.language_model.layers.44.linear_attn.norm", |
| "model.language_model.layers.44.post_attention_layernorm", |
| "model.language_model.layers.45.input_layernorm", |
| "model.language_model.layers.45.linear_attn.conv1d", |
| "model.language_model.layers.45.linear_attn.norm", |
| "model.language_model.layers.53.post_attention_layernorm", |
| "model.language_model.layers.54.input_layernorm", |
| "model.language_model.layers.54.linear_attn.conv1d", |
| "model.language_model.layers.54.linear_attn.norm", |
| "model.language_model.layers.54.post_attention_layernorm", |
| "model.language_model.layers.55.input_layernorm", |
| "model.language_model.layers.55.post_attention_layernorm", |
| "model.language_model.layers.55.self_attn.k_norm", |
| "model.language_model.layers.55.self_attn.q_norm", |
| "model.language_model.layers.48.input_layernorm", |
| "model.language_model.layers.48.linear_attn.conv1d", |
| "model.language_model.layers.48.linear_attn.norm", |
| "model.language_model.layers.48.post_attention_layernorm", |
| "model.language_model.layers.49.input_layernorm", |
| "model.language_model.layers.49.linear_attn.conv1d", |
| "model.language_model.layers.49.linear_attn.norm", |
| "model.language_model.layers.49.post_attention_layernorm", |
| "model.language_model.layers.50.input_layernorm", |
| "model.language_model.layers.50.linear_attn.conv1d", |
| "model.language_model.layers.50.linear_attn.norm", |
| "model.language_model.layers.50.post_attention_layernorm", |
| "model.language_model.layers.51.input_layernorm", |
| "model.language_model.layers.51.post_attention_layernorm", |
| "model.language_model.layers.51.self_attn.k_norm", |
| "model.language_model.layers.51.self_attn.q_norm", |
| "model.language_model.layers.52.input_layernorm", |
| "model.language_model.layers.52.linear_attn.conv1d", |
| "model.language_model.layers.52.linear_attn.norm", |
| "model.language_model.layers.52.post_attention_layernorm", |
| "model.language_model.layers.53.input_layernorm", |
| "model.language_model.layers.53.linear_attn.conv1d", |
| "model.language_model.layers.53.linear_attn.norm", |
| "model.language_model.layers.61.post_attention_layernorm", |
| "model.language_model.layers.62.input_layernorm", |
| "model.language_model.layers.62.linear_attn.conv1d", |
| "model.language_model.layers.62.linear_attn.norm", |
| "model.language_model.layers.62.post_attention_layernorm", |
| "model.language_model.layers.63.input_layernorm", |
| "model.language_model.layers.63.post_attention_layernorm", |
| "model.language_model.layers.63.self_attn.k_norm", |
| "model.language_model.layers.63.self_attn.q_norm", |
| "model.language_model.layers.56.input_layernorm", |
| "model.language_model.layers.56.linear_attn.conv1d", |
| "model.language_model.layers.56.linear_attn.norm", |
| "model.language_model.layers.56.post_attention_layernorm", |
| "model.language_model.layers.57.input_layernorm", |
| "model.language_model.layers.57.linear_attn.conv1d", |
| "model.language_model.layers.57.linear_attn.norm", |
| "model.language_model.layers.57.post_attention_layernorm", |
| "model.language_model.layers.58.input_layernorm", |
| "model.language_model.layers.58.linear_attn.conv1d", |
| "model.language_model.layers.58.linear_attn.norm", |
| "model.language_model.layers.58.post_attention_layernorm", |
| "model.language_model.layers.59.input_layernorm", |
| "model.language_model.layers.59.post_attention_layernorm", |
| "model.language_model.layers.59.self_attn.k_norm", |
| "model.language_model.layers.59.self_attn.q_norm", |
| "model.language_model.layers.60.input_layernorm", |
| "model.language_model.layers.60.linear_attn.conv1d", |
| "model.language_model.layers.60.linear_attn.norm", |
| "model.language_model.layers.60.post_attention_layernorm", |
| "model.language_model.layers.61.input_layernorm", |
| "model.language_model.layers.61.linear_attn.conv1d", |
| "model.language_model.layers.61.linear_attn.norm", |
| "model.language_model.norm" |
| ], |
| "provider": "auto-round" |
| } |
