llama-2-ko-70b-GPTQ / quantize_config.json
kuotient's picture
Upload folder using huggingface_hub
1e0e26c
raw
history blame contribute delete
208 Bytes
{
"bits": 4,
"group_size": -1,
"damp_percent": 0.1,
"desc_act": true,
"static_groups": false,
"sym": true,
"true_sequential": true,
"model_name_or_path": null,
"model_file_base_name": null
}