Llama-2-7B-Chat-GPTQ-marlin-4bit / quantize_config.json
aisuko's picture
Llama-2-7B-Chat-GPTQ-marlin-4bit
487049e verified
{
"bits": 4,
"group_size": 128,
"damp_percent": 0.01,
"desc_act": false,
"static_groups": false,
"sym": true,
"true_sequential": true,
"model_name_or_path": "TheBloke/Llama-2-7B-Chat-GPTQ",
"model_file_base_name": "model",
"quant_method": "gptq",
"checkpoint_format": "marlin"
}