Update README.md

README.md

@@ -43,7 +43,7 @@ cd $HOME/mistral-inference && poetry install .
 Note: 
 - **Important**:
   - `mixtral-8x22B-Instruct-v0.3.tar` is exactly the same as [Mixtral-8x22B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1), only stored in `.safetensors` format
-  - `mixtral-8x22B-v0.3.tar` is the same as [Mixtral-8x22B-v0.1](https://huggingface.co/mistralai/Mixtral-8x22B-v0.1), but has an extended vocabulary of 32756 tokens.
+  - `mixtral-8x22B-v0.3.tar` is the same as [Mixtral-8x22B-v0.1](https://huggingface.co/mistralai/Mixtral-8x22B-v0.1), but has an extended vocabulary of 32768 tokens.
 - All of the listed models above supports function calling. For example, Mistral 7B Base/Instruct v3 is a minor update to Mistral 7B Base/Instruct v2,  with the addition of function calling capabilities. 
 - The "coming soon" models will include function calling as well. 
 - You can download the previous versions of our models from our [docs](https://docs.mistral.ai/getting-started/open_weight_models/#downloading).