linzhao-amd commited on
Commit
d39da30
·
verified ·
1 Parent(s): 21582b4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -37,9 +37,8 @@ python3 quantize_quark.py --model_dir $MODEL_DIR \
37
  --quant_scheme w_mxfp4_a_mxfp4 \
38
  --group_size 32 \
39
  --num_calib_data 128 \
40
- --exclude_layers "*self_attn*" "*mlp.gate.*" "*lm_head" \
41
  --multi_gpu \
42
- --quant_algo autosmoothquant \
43
  --model_export hf_format \
44
  --output_dir amd/DeepSeek-R1-MXFP4
45
  ```
 
37
  --quant_scheme w_mxfp4_a_mxfp4 \
38
  --group_size 32 \
39
  --num_calib_data 128 \
40
+ --exclude_layers "*lm_head" \
41
  --multi_gpu \
 
42
  --model_export hf_format \
43
  --output_dir amd/DeepSeek-R1-MXFP4
44
  ```