NextStep-1.1-W4A16-AutoRound / quantization_config.json
xinhe's picture
Upload folder using huggingface_hub
63aad33 verified
raw
history blame contribute delete
299 Bytes
{
"bits": 4,
"data_type": "int",
"group_size": 128,
"sym": true,
"batch_size": 1,
"gradient_accumulate_steps": 8,
"autoround_version": "0.13.0",
"block_name_to_quantize": "layers,image_head.net.res_blocks",
"quant_method": "auto-round",
"packing_format": "auto_round:auto_gptq"
}