gemma-4-12b-it-uncensored-W4A16-AutoRound / quantization_config.json
hfacesp's picture
AutoRound W4A16 RTN quant (Gemma 4 12B Unified abliterated)
f729865 verified
Raw
History Blame Contribute Delete
293 Bytes
{
"bits": 4,
"data_type": "int",
"group_size": 128,
"sym": true,
"enable_quanted_input": false,
"nsamples": 256,
"autoround_version": "0.14.0",
"block_name_to_quantize": "model.language_model.layers",
"quant_method": "auto-round",
"packing_format": "auto_round:auto_gptq"
}