{ "bits": 4, "group_size": 128, "sym": true, "data_type": "int", "enable_quanted_input": true, "enable_minmax_tuning": true, "seqlen": 512, "batch_size": 1, "scale_dtype": "torch.float16", "lr": 0.005, "minmax_lr": 0.005, "gradient_accumulate_steps": 8, "iters": 200, "amp": true, "nsamples": 128, "low_gpu_mem_usage": false, "to_quant_block_names": "language_model.model.layers", "enable_norm_bias_tuning": false, "autoround_version": "0.4.2.dev", "block_name_to_quantize": "language_model.model.layers", "quant_method": "gptq", "desc_act": false, "true_sequential": false, "damp_percent": 0.01 }