Text Generation
Transformers
llama
Inference Endpoints
airophin-13b-pntk-16k-GPTQ / quantize_config.json
bhenrym14's picture
Upload 7 files
d4d8959
raw
history blame
183 Bytes
{
"bits": 4,
"group_size": 32,
"damp_percent": 0.01,
"desc_act": true,
"sym": true,
"true_sequential": true,
"model_name_or_path": null,
"model_file_base_name": null
}