Update app.py

app.py

@@ -5,6 +5,7 @@ import os
 # Load secrets
 system_message = os.environ["SYSTEM_MESSAGE"]
 HF_TOKEN = os.environ["HF_TOKEN"]
+MODEL_NAME = os.environ["MODEL_NAME"]  # <-- Add this
 
 client = InferenceClient(token=HF_TOKEN)
 
@@ -18,7 +19,7 @@ def respond(message, history, max_tokens, temperature, top_p):
 
     response = []
     stream = client.chat.completions.create(
-        model="mistralai/Mistral-7B-Instruct-v0.3",
+        model=MODEL_NAME,  # <-- use the secret here
         messages=prompt,
         max_tokens=max_tokens,
         temperature=temperature,
@@ -26,14 +27,13 @@ def respond(message, history, max_tokens, temperature, top_p):
         stream=True
     )
 
-    # Fast generator (yield only when new content available)
     for chunk in stream:
         token = chunk.choices[0].delta.content
         if token:
             response.append(token)
             yield "".join(response)
 
-# UI (clean and efficient)
+# UI
 app = gr.ChatInterface(
     fn=respond,
     additional_inputs=[
@@ -41,9 +41,7 @@ app = gr.ChatInterface(
         gr.Slider(0.1, 2.0, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(0.1, 1.0, value=0.95, step=0.05, label="Top-p"),
     ],
-
 )
 
 if __name__ == "__main__":
     app.launch()
-