Update README.md

README.md

@@ -119,9 +119,9 @@ You can directly pass tools as JSON schema or Python functions with `.apply_chat
 
 ### 1. Transformers
 
-To run LFM2, you need to install Hugging Face [`transformers`](https://github.com/huggingface/transformers) from source as follows:
+To run LFM2, you need to install Hugging Face [`transformers`](https://github.com/huggingface/transformers):
 ```bash
-pip install git+https://github.com/huggingface/transformers.git@0c9a72e4576fe4c84077f066e585129c97bfd4e6
+pip install transformers
 ```
 
 Here is an example of how to generate an answer with transformers in Python:
@@ -221,7 +221,6 @@ for i, output in enumerate(outputs):
     print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
 ```
 
-
 ### 3. llama.cpp
 
 You can run LFM2 with llama.cpp using its [GGUF checkpoint](https://huggingface.co/LiquidAI/LFM2-8B-A1B-GGUF). Find more information in the model card.