Qwen-7B-Chat-GPTQ / quantize_config.json
basiliskinstitute's picture
Upload 14 files
1edc3a9
raw
history blame contribute delete
210 Bytes
{
"bits": 4,
"group_size": -1,
"damp_percent": 0.01,
"desc_act": false,
"static_groups": false,
"sym": true,
"true_sequential": true,
"model_name_or_path": null,
"model_file_base_name": null
}