Text Generation
Transformers
Safetensors
mixtral
conversational
text-generation-inference
4-bit precision
gptq
bagel-dpo-8x7b-v0.2-GPTQ / quantize_config.json
TheBloke's picture
GPTQ model commit
ab77d60 verified
{
"bits": 8,
"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": "model"
}