baichuan2-13b-chat-gptq-32g-act / quantize_config.json
yfshi123's picture
Upload of AutoGPTQ quantized model
01e6a84
raw
history blame contribute delete
209 Bytes
{
"bits": 4,
"group_size": 32,
"damp_percent": 0.01,
"desc_act": true,
"static_groups": false,
"sym": true,
"true_sequential": true,
"model_name_or_path": null,
"model_file_base_name": null
}