Add system prompt, add correct stop tokens

app.py

@@ -1,3 +1,49 @@
+Hugging Face's logo
+Hugging Face
+Search models, datasets, users...
+Models
+Datasets
+Spaces
+Posts
+Docs
+Solutions
+Pricing
+
+
+
+Spaces:
+
+Sadmank
+/
+reflection
+
+private
+
+Logs
+App
+Files
+Community
+Settings
+reflection
+/
+app.py
+
+Sadmank's picture
+Sadmank
+Update app.py
+6c53f07
+verified
+3 minutes ago
+raw
+
+Copy download link
+history
+blame
+edit
+delete
+No virus
+
+5.92 kB
 import gradio as gr
 import requests
 import os
@@ -86,9 +132,12 @@ def stream_response(message, history, max_tokens, temperature, top_p):
         "messages": messages,
         "max_tokens": max_tokens,
         "temperature": temperature,
+        "system" : "You are a world-class AI system, capable of complex reasoning and reflection. Reason through the query inside <thinking> tags, and then provide your final response inside <output> tags. If you detect that you made a mistake in your reasoning at any point, correct yourself inside <reflection> tags.",
         "top_p": top_p,
         "stream": True,
-        "stop": ["</output>"]  # Add stop sequence
+        "stop": [ "<|start_header_id|>",
+        "<|end_header_id|>",
+        "<|eot_id|>"]  # Add stop sequence
     }
     
     debug_print(f"Sending request to API: {API_URL}")