| { |
| "config_groups": { |
| "group_0": { |
| "targets": [ |
| "Linear" |
| ], |
| "weights": { |
| "num_bits": 4, |
| "type": "int", |
| "symmetric": true, |
| "group_size": 32, |
| "strategy": "group", |
| "block_structure": null, |
| "dynamic": false, |
| "actorder": null, |
| "scale_dtype": null, |
| "zp_dtype": null, |
| "observer": "memoryless_minmax", |
| "observer_kwargs": {} |
| }, |
| "input_activations": null, |
| "output_activations": null, |
| "format": "pack-quantized" |
| } |
| }, |
| "quant_method": "compressed-tensors", |
| "kv_cache_scheme": null, |
| "format": "pack-quantized", |
| "quantization_status": "compressed", |
| "global_compression_ratio": null, |
| "ignore": [ |
| "model.visual.blocks.0.attn.qkv", |
| "model.visual.blocks.0.attn.proj", |
| "model.visual.blocks.0.mlp.linear_fc1", |
| "model.visual.blocks.0.mlp.linear_fc2", |
| "model.visual.blocks.1.attn.qkv", |
| "model.visual.blocks.1.attn.proj", |
| "model.visual.blocks.1.mlp.linear_fc1", |
| "model.visual.blocks.1.mlp.linear_fc2", |
| "model.visual.blocks.2.attn.qkv", |
| "model.visual.blocks.2.attn.proj", |
| "model.visual.blocks.2.mlp.linear_fc1", |
| "model.visual.blocks.2.mlp.linear_fc2", |
| "model.visual.blocks.3.attn.qkv", |
| "model.visual.blocks.3.attn.proj", |
| "model.visual.blocks.3.mlp.linear_fc1", |
| "model.visual.blocks.3.mlp.linear_fc2", |
| "model.visual.blocks.4.attn.qkv", |
| "model.visual.blocks.4.attn.proj", |
| "model.visual.blocks.4.mlp.linear_fc1", |
| "model.visual.blocks.4.mlp.linear_fc2", |
| "model.visual.blocks.5.attn.qkv", |
| "model.visual.blocks.5.attn.proj", |
| "model.visual.blocks.5.mlp.linear_fc1", |
| "model.visual.blocks.5.mlp.linear_fc2", |
| "model.visual.blocks.6.attn.qkv", |
| "model.visual.blocks.6.attn.proj", |
| "model.visual.blocks.6.mlp.linear_fc1", |
| "model.visual.blocks.6.mlp.linear_fc2", |
| "model.visual.blocks.7.attn.qkv", |
| "model.visual.blocks.7.attn.proj", |
| "model.visual.blocks.7.mlp.linear_fc1", |
| "model.visual.blocks.7.mlp.linear_fc2", |
| "model.visual.blocks.8.attn.qkv", |
| "model.visual.blocks.8.attn.proj", |
| "model.visual.blocks.8.mlp.linear_fc1", |
| "model.visual.blocks.8.mlp.linear_fc2", |
| "model.visual.blocks.9.attn.qkv", |
| "model.visual.blocks.9.attn.proj", |
| "model.visual.blocks.9.mlp.linear_fc1", |
| "model.visual.blocks.9.mlp.linear_fc2", |
| "model.visual.blocks.10.attn.qkv", |
| "model.visual.blocks.10.attn.proj", |
| "model.visual.blocks.10.mlp.linear_fc1", |
| "model.visual.blocks.10.mlp.linear_fc2", |
| "model.visual.blocks.11.attn.qkv", |
| "model.visual.blocks.11.attn.proj", |
| "model.visual.blocks.11.mlp.linear_fc1", |
| "model.visual.blocks.11.mlp.linear_fc2", |
| "model.visual.blocks.12.attn.qkv", |
| "model.visual.blocks.12.attn.proj", |
| "model.visual.blocks.12.mlp.linear_fc1", |
| "model.visual.blocks.12.mlp.linear_fc2", |
| "model.visual.blocks.13.attn.qkv", |
| "model.visual.blocks.13.attn.proj", |
| "model.visual.blocks.13.mlp.linear_fc1", |
| "model.visual.blocks.13.mlp.linear_fc2", |
| "model.visual.blocks.14.attn.qkv", |
| "model.visual.blocks.14.attn.proj", |
| "model.visual.blocks.14.mlp.linear_fc1", |
| "model.visual.blocks.14.mlp.linear_fc2", |
| "model.visual.blocks.15.attn.qkv", |
| "model.visual.blocks.15.attn.proj", |
| "model.visual.blocks.15.mlp.linear_fc1", |
| "model.visual.blocks.15.mlp.linear_fc2", |
| "model.visual.blocks.16.attn.qkv", |
| "model.visual.blocks.16.attn.proj", |
| "model.visual.blocks.16.mlp.linear_fc1", |
| "model.visual.blocks.16.mlp.linear_fc2", |
| "model.visual.blocks.17.attn.qkv", |
| "model.visual.blocks.17.attn.proj", |
| "model.visual.blocks.17.mlp.linear_fc1", |
| "model.visual.blocks.17.mlp.linear_fc2", |
| "model.visual.blocks.18.attn.qkv", |
| "model.visual.blocks.18.attn.proj", |
| "model.visual.blocks.18.mlp.linear_fc1", |
| "model.visual.blocks.18.mlp.linear_fc2", |
| "model.visual.blocks.19.attn.qkv", |
| "model.visual.blocks.19.attn.proj", |
| "model.visual.blocks.19.mlp.linear_fc1", |
| "model.visual.blocks.19.mlp.linear_fc2", |
| "model.visual.blocks.20.attn.qkv", |
| "model.visual.blocks.20.attn.proj", |
| "model.visual.blocks.20.mlp.linear_fc1", |
| "model.visual.blocks.20.mlp.linear_fc2", |
| "model.visual.blocks.21.attn.qkv", |
| "model.visual.blocks.21.attn.proj", |
| "model.visual.blocks.21.mlp.linear_fc1", |
| "model.visual.blocks.21.mlp.linear_fc2", |
| "model.visual.blocks.22.attn.qkv", |
| "model.visual.blocks.22.attn.proj", |
| "model.visual.blocks.22.mlp.linear_fc1", |
| "model.visual.blocks.22.mlp.linear_fc2", |
| "model.visual.blocks.23.attn.qkv", |
| "model.visual.blocks.23.attn.proj", |
| "model.visual.blocks.23.mlp.linear_fc1", |
| "model.visual.blocks.23.mlp.linear_fc2", |
| "model.visual.merger.linear_fc1", |
| "model.visual.merger.linear_fc2", |
| "model.language_model.layers.0.linear_attn", |
| "model.language_model.layers.0.linear_attn.norm", |
| "model.language_model.layers.1.linear_attn", |
| "model.language_model.layers.1.linear_attn.norm", |
| "model.language_model.layers.2.linear_attn", |
| "model.language_model.layers.2.linear_attn.norm", |
| "model.language_model.layers.4.linear_attn", |
| "model.language_model.layers.4.linear_attn.norm", |
| "model.language_model.layers.5.linear_attn", |
| "model.language_model.layers.5.linear_attn.norm", |
| "model.language_model.layers.6.linear_attn", |
| "model.language_model.layers.6.linear_attn.norm", |
| "model.language_model.layers.8.linear_attn", |
| "model.language_model.layers.8.linear_attn.norm", |
| "model.language_model.layers.9.linear_attn", |
| "model.language_model.layers.9.linear_attn.norm", |
| "model.language_model.layers.10.linear_attn", |
| "model.language_model.layers.10.linear_attn.norm", |
| "model.language_model.layers.12.linear_attn", |
| "model.language_model.layers.12.linear_attn.norm", |
| "model.language_model.layers.13.linear_attn", |
| "model.language_model.layers.13.linear_attn.norm", |
| "model.language_model.layers.14.linear_attn", |
| "model.language_model.layers.14.linear_attn.norm", |
| "model.language_model.layers.16.linear_attn", |
| "model.language_model.layers.16.linear_attn.norm", |
| "model.language_model.layers.17.linear_attn", |
| "model.language_model.layers.17.linear_attn.norm", |
| "model.language_model.layers.18.linear_attn", |
| "model.language_model.layers.18.linear_attn.norm", |
| "model.language_model.layers.20.linear_attn", |
| "model.language_model.layers.20.linear_attn.norm", |
| "model.language_model.layers.21.linear_attn", |
| "model.language_model.layers.21.linear_attn.norm", |
| "model.language_model.layers.22.linear_attn", |
| "model.language_model.layers.22.linear_attn.norm", |
| "model.language_model.layers.24.linear_attn", |
| "model.language_model.layers.24.linear_attn.norm", |
| "model.language_model.layers.25.linear_attn", |
| "model.language_model.layers.25.linear_attn.norm", |
| "model.language_model.layers.26.linear_attn", |
| "model.language_model.layers.26.linear_attn.norm", |
| "model.language_model.layers.28.linear_attn", |
| "model.language_model.layers.28.linear_attn.norm", |
| "model.language_model.layers.29.linear_attn", |
| "model.language_model.layers.29.linear_attn.norm", |
| "model.language_model.layers.30.linear_attn", |
| "model.language_model.layers.30.linear_attn.norm", |
| "lm_head" |
| ] |
| } |
