Update model_api.py

model_api.py

@@ -1,22 +1,22 @@
+import streamlit as st
 from huggingface_hub import InferenceClient
-import os
 
 def query_model(prompt):
+
     try:
-        HF_TOKEN = os.getenv("HF_TOKEN")
+        HF_TOKEN = st.secrets["HF_TOKEN"]
 
         client = InferenceClient(
-            model="llama-3.1-8b-i",
+            model="meta-llama/Meta-Llama-3-8B-Instruct",
             token=HF_TOKEN
         )
 
         response = client.chat_completion(
             messages=[
-                {"role": "system", "content": "You are a certified professional fitness trainer."},
+                {"role": "system", "content": "You are a certified fitness trainer."},
                 {"role": "user", "content": prompt}
             ],
-            max_tokens=2000,
-            temperature=0.7
+            max_tokens=800
         )
 
         return response.choices[0].message.content