qwen2-vl-infer / quantize_config.json
morthens's picture
Duplicate from Qwen/Qwen2-VL-7B-Instruct-GPTQ-Int4
5a8a6ea verified
raw
history blame
207 Bytes
{
"bits": 4,
"dataset": null,
"group_size": 128,
"damp_percent": 0.1,
"desc_act": false,
"sym": true,
"true_sequential": true,
"quant_method": "gptq",
"modules_in_block_to_quantize": null
}