Update README.md

README.md

@@ -298,11 +298,10 @@ print(output_text)
 - Minimum VRAM: 120 GB (e.g., Mac studio, DGX-Spark, AMD Ryzen AI Max+ 395)
 - Recommended: 128GB unified memory
 #### Steps
-1. Clone llama.cpp and checkout to step3.5 branch:
+1. Use llama.cpp:
 ```bash
-git clone https://github.com/stepfun-ai/Step-3.5-Flash.git
-cd llama.cpp
-git checkout feature/step3.5-flash
+git clone git@github.com:stepfun-ai/Step-3.5-Flash.git
+cd Step-3.5-Flash/llama.cpp
 ```
 2. Build llama.cpp on Mac:
 ```bash