amd
/

DeepSeek-R1-MXFP4-ASQ

8-bit precision

Model card Files Files and versions

linzhao-amd commited on Nov 6

Commit

b9c0909

·

verified ·

1 Parent(s): 77de8ba

Update README.md

Files changed (1) hide show

README.md +1 -0

README.md CHANGED Viewed

@@ -39,6 +39,7 @@ python3 quantize_quark.py --model_dir $MODEL_DIR \
                           --group_size 32 \
                           --num_calib_data 128 \
                           --exclude_layers $exclude_layers \
                           --multi_gpu \
                           --quant_algo autosmoothquant \
                           --model_export hf_format \

                           --group_size 32 \
                           --num_calib_data 128 \
                           --exclude_layers $exclude_layers \
+                          --skip_evaluation \
                           --multi_gpu \
                           --quant_algo autosmoothquant \
                           --model_export hf_format \