Qwen3.5-4B-AutoRound-MXFP8-Tuning / quantization_config.json
INC4AI's picture
Upload quantized model Qwen3.5-4B-AutoRound-MXFP8-Tuning
02db315 verified
Raw
History Blame Contribute Delete
405 Bytes
{
"bits": 8,
"act_bits": 8,
"data_type": "mx_fp",
"act_data_type": "mx_fp",
"group_size": 32,
"act_group_size": 32,
"sym": true,
"act_sym": true,
"act_dynamic": true,
"low_gpu_mem_usage": true,
"seqlen": 1024,
"autoround_version": "0.14.2",
"block_name_to_quantize": "model.language_model.layers",
"quant_method": "auto-round",
"packing_format": "auto_round:llm_compressor"
}