XVERSE-13B-Chat-GPTQ-Int4 / quantize_config.json
willhe-xverse's picture
Upload folder using huggingface_hub
b22367a verified
raw
history blame
392 Bytes
{
"bits": 4,
"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/willhe/github/AutoGPTQ/examples/quantization/xverse-13b-fanyule847491-1204_xland-1226-4bit-128g",
"model_file_base_name": "gptq_model-4bit-128g",
"is_marlin_format": false,
"quant_method": "gptq"
}