| { | |
| "quant_method": "gptq", | |
| "bits": 4, | |
| "tokenizer": null, | |
| "dataset": "c4", | |
| "group_size": 128, | |
| "damp_percent": 0.1, | |
| "desc_act": false, | |
| "sym": true, | |
| "true_sequential": true, | |
| "use_cuda_fp16": false, | |
| "model_seqlen": null, | |
| "block_name_to_quantize": null, | |
| "module_name_preceding_first_block": null, | |
| "batch_size": 1, | |
| "pad_token_id": null, | |
| "use_exllama": true, | |
| "max_input_length": null, | |
| "exllama_config": { | |
| "version": 1 | |
| }, | |
| "cache_block_outputs": true, | |
| "modules_in_block_to_quantize": null | |
| } |