llama-2-7b_wanda_2_4_gptq_4bit_128g / quantize_config.json
jyhong836's picture
Upload quantize_config.json with huggingface_hub
29e1ec4
raw
history blame
263 Bytes
{
"bits": 4,
"group_size": 128,
"damp_percent": 0.01,
"desc_act": true,
"static_groups": false,
"sym": true,
"true_sequential": true,
"model_name_or_path": "zoo/zhenyu/llama2/wanda_2_4_gptq_4bit",
"model_file_base_name": "gptq_model-4bit-128g"
}