Text Generation
Transformers
Safetensors
English
llama
text-generation-inference
4-bit precision
gptq
wizard-mega-13B-GPTQ / quantize_config.json
TheBloke's picture
Update for Transformers GPTQ support
848bf25
raw
history blame
158 Bytes
{
"bits": 4,
"group_size": 128,
"damp_percent": 0.01,
"desc_act": false,
"sym": true,
"true_sequential": true,
"model_file_base_name": "model"
}