Update README.md

README.md

@@ -196,7 +196,7 @@ messages.append(
 
 # Running the model on a CPU
 
-This repo contains quantized (q8) version of the model as well. You can use the model on your local machine (without gpu) as explained [here](docs https://github.com/ggml-org/llama.cpp/tree/master/tools/main).
+This repo contains gguf versions of `sarvam-m` in both bf16 and q8 precisions. You can use the model on your local machine (without gpu) as explained [here](https://github.com/ggml-org/llama.cpp/tree/master/tools/main).
 
 Example Command:
 ```