| { | |
| "autoround_version": "0.14.0", | |
| "batch_size": 1, | |
| "bits": 4, | |
| "block_name_to_quantize": [ | |
| "language_model.layers", | |
| "gen_layers", | |
| "blocks", | |
| "deepstack_merger_list" | |
| ], | |
| "data_type": "int", | |
| "group_size": 128, | |
| "nsamples": 16, | |
| "packing_format": "auto_round:auto_gptq", | |
| "quant_method": "auto-round", | |
| "sym": true | |
| } |