Hugging Face's logo

jiaxwang
/
test

Model card Files
xet
Community
jiaxwang commited on
Commit
add62b8
·
verified ·
1 Parent(s): 6d4edc4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -40,7 +40,7 @@ python3 internal_scripts/quantize_quark.py \
40
  --attention_dtype fp8 \
41
  --exclude_layers $exclude_layers \
42
  --num_calib_data 512 \
43
- --output_dir amd/gpt-oss120b-w-mxfp4-a-fp8 \
44
  --model_export hf_format \
45
  --multi_gpu
46
  ```
 
40
  --attention_dtype fp8 \
41
  --exclude_layers $exclude_layers \
42
  --num_calib_data 512 \
43
+ --output_dir amd/gpt-oss120b-moe_w-mxfp4-a-fp8-attn_ptpc-kv-soft_fp8 \
44
  --model_export hf_format \
45
  --multi_gpu
46
  ```