Qwen3-Omni-30B-A3B-Instruct-int4-AutoRound / quantization_config.json
lianglv's picture
Upload folder using huggingface_hub
8448e02 verified
raw
history blame contribute delete
368 Bytes
{
"bits": 4,
"data_type": "int",
"group_size": 128,
"sym": true,
"autoround_version": "0.13.0",
"block_name_to_quantize": "thinker.model.layers",
"quant_method": "auto-round",
"packing_format": "auto_round:auto_gptq",
"extra_config": {
".*thinker\\.model\\.layers\\.\\d+\\.mlp\\.gate.*": {
"bits": 16,
"data_type": "float"
}
}
}