Text Generation
Transformers
Chinese
llama
text-generation-inference
Taiwan-LLaMa-v1.0-4bits-GPTQ / quantize_config.json
weiren119's picture
feat: convert Taiwan Llama2 with gptq
d48af6f
{
"bits": 4,
"group_size": 128,
"damp_percent": 0.01,
"desc_act": false,
"sym": true,
"true_sequential": true,
"model_name_or_path": "Taiwan-LLaMa-v1.0-4bits-GPTQ",
"model_file_base_name": "gptq_model-4bit-128g"
}