Text Generation
Transformers
Safetensors
llama
text-generation-inference
4-bit precision
gptq
PuddleJumper-13B-V2-GPTQ / quantize_config.json
TheBloke's picture
GPTQ model commit
f582e31
raw
history blame
186 Bytes
{
"bits": 4,
"group_size": 128,
"damp_percent": 0.1,
"desc_act": true,
"sym": true,
"true_sequential": true,
"model_name_or_path": null,
"model_file_base_name": "model"
}