Update model.py, change model to gemma-7b-it

model.py

@@ -44,7 +44,7 @@ def ask(query, temperature=0.7, max_new_tokens=512):
 
     # Load HF token from Secrets (set this in your Space Settings > Secrets)
     HF_TOKEN = os.getenv("HF_TOKEN")
-    model_id = "google/gemma-2-2b-it"
+    model_id = "google/gemma-7b-it"
 
     # Load LLM if not already loaded
     if llm_model is None or tokenizer is None:
@@ -75,6 +75,7 @@ def ask(query, temperature=0.7, max_new_tokens=512):
     # Clean up output
     if "Answer:" in output_text:
         output_text = output_text.split("Answer:")[-1].strip()
+        output_text = output_text.split("model")[-1].strip()
     return output_text