Update README.md

README.md

@@ -88,7 +88,7 @@ We recommand that you use Mistral-Small-Instruct-2501 in a server/client setting
 1. Spin up a server:
 
 ```
-vllm serve mistralai/Mistral-Small-Instruct-2501 --tokenizer_mode mistral --config_format mistral --load_format mistral --enable-auto-tool-choice
+vllm serve mistralai/Mistral-Small-24B-Instruct-2501 --tokenizer_mode mistral --config_format mistral --load_format mistral --enable-auto-tool-choice
 ```
 
 **Note:** Running Mistral-Small-Instruct-2501 on GPU requires 60 GB of GPU RAM. 
@@ -104,7 +104,7 @@ from datetime import datetime, timedelta
 url = "http://<your-server>:8000/v1/chat/completions"
 headers = {"Content-Type": "application/json", "Authorization": "Bearer token"}
 
-model = "mistralai/Mistral-Small-Instruct-2501"
+model = "mistralai/Mistral-Small-24B-Instruct-2501"
 
 messages = [
     {
@@ -193,7 +193,7 @@ messages = [
     {"role": "system", "content": "You are a conversational agent that always answers straight to the point, always end your accurate response with an ASCII drawing of a cat."},
     {"role": "user", "content": "Give me 5 non-formal ways to say 'See you later' in French."},
 ]
-chatbot = pipeline("text-generation", model="mistralai/Mistral-Small-Instruct-2501", max_new_tokens=256)
+chatbot = pipeline("text-generation", model="mistralai/Mistral-Small-24B-Instruct-2501", max_new_tokens=256)
 chatbot(messages)
 ```