Update README.md

README.md

@@ -21,7 +21,14 @@ This model is an advanced fp8 quantized version of google/gemma-3-27b-it, meticu
    
 
 
- ## Inference with HuggingFace
+ # Inference with HuggingFace
+
+ ## Transformers library
+
+```sh
+ pip install git+https://github.com/huggingface/[email protected]
+```
+
  ```python3
  
 from transformers import AutoProcessor, Gemma3ForConditionalGeneration, BitsAndBytesConfig