Update server.py

server.py

@@ -1289,7 +1289,7 @@ def generate_text_only(req: TextGenerationRequest):
                 max_new_tokens=2048,  # HARDCODED - same as chat() function
                 do_sample=True,
                 temperature=0.20,  # HARDCODED - same as chat() function
-                repetition_penalty=1.15,  # Better repetition control
+                repetition_penalty=1.1,  # Better repetition control
                 top_k=100,  # Balanced vocabulary selection
                 top_p=0.95,  # HARDCODED - same as chat() function
                 num_beams=1,  # Single beam for faster generation
@@ -1420,6 +1420,7 @@ def generate_text(req: GenerateRequest):
 3 points: The response is relevant and mostly accurate,  may lack conciseness or include unnecessary details that don't contribute to the main point.
 4 points: The response is relevant, accurate, and concise, providing a clear answer to the user's question without unnecessary elaboration.
 5 points: The response is exceptionally relevant, accurate, and to the point. It directly addresses the user's query in a highly effective and efficient manner, providing exactly the information needed.
+10 points: The response is the best that any LLM can give. 
 
 You need to give a response with score GREATER than 5 points, i.e 5+.