| { |
| "bits": 4, |
| "dynamic": { |
| "-:.*linear_attn\\.in_proj_qkv": {}, |
| "-:.*linear_attn\\.in_proj_z": {}, |
| "-:.*linear_attn\\.out_proj": {}, |
| "-:.*shared_expert\\.gate_proj": {}, |
| "-:.*shared_expert\\.up_proj": {}, |
| "-:.*shared_expert\\.down_proj": {} |
| }, |
| "group_size": 32, |
| "desc_act": false, |
| "lm_head": false, |
| "method": "gptq", |
| "quant_method": "gptq", |
| "format": "gptq", |
| "checkpoint_format": "gptq", |
| "pack_dtype": "int32", |
| "meta": { |
| "quantizer": [ |
| "gptqmodel:6.0.3" |
| ], |
| "uri": "https://github.com/modelcloud/gptqmodel", |
| "damp_percent": 0.05, |
| "damp_auto_increment": 0.01, |
| "static_groups": false, |
| "true_sequential": true, |
| "mse": 0.0, |
| "gptaq": null, |
| "foem": null, |
| "act_group_aware": true, |
| "fallback": { |
| "strategy": "rtn", |
| "threshold": "0.5%", |
| "smooth": null |
| }, |
| "offload_to_disk": false, |
| "offload_to_disk_path": null, |
| "pack_impl": "cpu", |
| "gc_mode": "interval", |
| "wait_for_submodule_finalizers": false, |
| "auto_forward_data_parallel": true, |
| "vram_strategy": "exclusive", |
| "mock_quantization": false, |
| "hessian": { |
| "chunk_size": null, |
| "chunk_bytes": null, |
| "staging_dtype": "float32" |
| } |
| }, |
| "sym": true |
| } |
