Update README.md

README.md

@@ -56,7 +56,7 @@ python3 quantize_quark.py --model_dir "${MODEL}" \
                           --model_export hf_format \
                           --custom_mode fp8 \
                           --quant_algo autosmoothquant \
-                          --exclude_layers "lm_head" "*.gate"
+                          --exclude_layers "lm_head" "*.gate" "*.o_proj"
 ```
 
 # Model Performance Comparison