FLUX.1-dev-AutoRound-w4a16 / transformer /quantization_config.json
Yi30's picture
Upload folder using huggingface_hub
f83f378 verified
raw
history blame contribute delete
291 Bytes
{
"bits": 4,
"data_type": "int",
"group_size": 128,
"sym": true,
"batch_size": 1,
"iters": 0,
"autoround_version": "0.12.0",
"block_name_to_quantize": "transformer_blocks,single_transformer_blocks",
"quant_method": "auto-round",
"packing_format": "auto_round:auto_gptq"
}