Update app.py

app.py

@@ -10,13 +10,12 @@ HF_API_TOKEN = os.getenv("HF_TOKEN")
 
 def get_hf_model():
     return InferenceClientModel(
-        model_id="Qwen/Qwen2.5-Coder-32B-Instruct",
-        # provider="auto", # You can omit this, 'auto' is the default
-        token=HF_API_TOKEN, # Use 'token' instead of 'api_key'
-        temperature=0.2,
-        max_tokens=8192,
-        timeout=120,
-    )
+            model_id="mistralai/Mistral-7B-Instruct-v0.3",
+            token=HF_API_TOKEN,
+            temperature=0.2,
+            max_tokens=4096,  # Smaller models have smaller context windows
+            timeout=120,
+        )
 
 # Make sure to update this line too
 MODEL = get_hf_model()