gpt2-xl-AutoGPTQ-4bit-128g / quantize_config.json
smpanaro's picture
Upload of AutoGPTQ quantized model
a7d67bd verified
raw
history blame
299 Bytes
{
"bits": 4,
"group_size": 128,
"damp_percent": 0.01,
"desc_act": false,
"static_groups": false,
"sym": true,
"true_sequential": true,
"model_name_or_path": "gpt2-xl-4bit-128g",
"model_file_base_name": "gptq_model-4bit-128g",
"is_marlin_format": false,
"quant_method": "gptq"
}