Qwen3-VL-2B-Instruct-W4A16 / .ipynb_checkpoints /quantization_config-checkpoint.json
bnjmnmarie's picture
Upload folder using huggingface_hub
adb7eab verified
{
"bits": 4,
"group_size": 128,
"sym": true,
"data_type": "int",
"autoround_version": "0.8.0",
"block_name_to_quantize": "model.language_model.layers",
"quant_method": "auto-round",
"packing_format": "auto_round:auto_gptq"
}