Update README.md

README.md

@@ -12,3 +12,12 @@ The models are quantized via [Ryzen AI SW 1.2](https://github.com/amd/RyzenAI-SW
 
 The folder `quantized_models` contains a set of LLMs quantized via different algorithms.    
 The folder `onnx_model_nodes` contains a set of `mlp.up_proj` nodes for `-npugpu` device parallel config. 
+
+Due to the miscellaneous Python environment of Ryzen AI. You may need to install different versions of transformers:
+```python
+transformers==4.37.2  # Others
+transformers==4.39.1  # GEMMA
+transformers>=4.42  # Mistral
+```
+
+