| { | |
| "bits": 4, | |
| "data_type": "int", | |
| "group_size": 32, | |
| "sym": true, | |
| "iters": 800, | |
| "autoround_version": "0.16.0", | |
| "block_name_to_quantize": "model.language_model.layers", | |
| "quant_method": "auto-round", | |
| "packing_format": "auto_round:auto_gptq", | |
| "extra_config": { | |
| ".*\\*\\.linear_conv.*": { | |
| "data_type": "bfloat16" | |
| }, | |
| ".*\\*\\.conv1d.*": { | |
| "data_type": "bfloat16" | |
| } | |
| } | |
| } |