Update README.md

README.md

@@ -28,6 +28,8 @@ The model is distilled from the original DeepSeek-R1 and uses the Qwen-2.5-7B ar
 - **Quantization:** 4-bit NormalFloat (NF4) for optimized memory usage.
 
 ## Usage
+```python
+pip install -U transformers -U bitsandbytes>=0.46.1
 
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer