opt-125m-2bit / quantize_config.json
lebe1's picture
AutoGPTQ model for facebook/opt-125m: 2bits, gr128, desc_act=False
750949f
{
"bits": 2,
"group_size": 128,
"damp_percent": 0.01,
"desc_act": false,
"static_groups": false,
"sym": true,
"true_sequential": true,
"model_name_or_path": "opt-125m-2bit",
"model_file_base_name": "gptq_model-2bit-128g"
}