llama2_7b_chat_uncensored-GPTQ / quantize_config.json
TheBloke's picture
Update for Transformers GPTQ support
d3d690c
raw
history blame
188 Bytes
{
"bits": 4,
"group_size": 128,
"damp_percent": 0.01,
"desc_act": false,
"sym": true,
"true_sequential": true,
"model_name_or_path": null,
"model_file_base_name": "model"
}