Qwen-14B-Chat-Int8 / quantize_config.json
yangapku's picture
update int8 quantization info
4bf9d82
raw
history blame
214 Bytes
{
"bits": 8,
"group_size": 128,
"damp_percent": 0.01,
"desc_act": false,
"static_groups": false,
"sym": true,
"true_sequential": true,
"model_name_or_path": null,
"model_file_base_name": "model"
}