opt-125m-4bit-128g / quantize_config.json
Technotech's picture
AutoGPTQ model for facebook/opt-125m: 4bits, gr128, desc_act=False
45574a7
{
"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": null
}