Ornith-1.0-9B-MTP-int4-AutoRound / quantization_config.json
urakozz's picture
Upload folder using huggingface_hub
050febe verified
Raw
History Blame Contribute Delete
295 Bytes
{
"bits": 4,
"data_type": "int",
"group_size": 64,
"sym": true,
"lr": 0.001,
"minmax_lr": 0.001,
"nsamples": 64,
"autoround_version": "0.15.0",
"block_name_to_quantize": "model.language_model.layers",
"quant_method": "auto-round",
"packing_format": "auto_round:auto_gptq"
}