XVERSE-13B-Chat-GPTQ-Int8 / quantize_config.json
willhe-xverse's picture
Upload folder using huggingface_hub
532b134 verified
{
"bits": 8,
"group_size": 128,
"damp_percent": 0.01,
"desc_act": true,
"static_groups": true,
"sym": true,
"true_sequential": true,
"model_name_or_path": "/mnt/llm_dataset/xverse_models/gptq/XVERSE-13B-Chat-GPTQ-Int8",
"model_file_base_name": "gptq_model-8bit-128g",
"is_marlin_format": false,
"quant_method": "gptq"
}