opt-13b-GPTQ-4bit-g128 / quantize_config.json
iproskurina's picture
AutoGPTQ model for facebook/opt-13b: 4bits, gr128, desc_act=False
bcdf4a2 verified
raw
history blame contribute delete
211 Bytes
{
"bits": 4,
"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": null
}