Update app.py

app.py

@@ -106,26 +106,17 @@ if prompt := st.chat_input(f"Hi I'm {selected_model}, How can I help you today?"
     
     formatted_text = format_prompt(prompt, conversation_history, custom_instruction)
     
-    max_tokens = {
-        "LegacyLift🚀": 32000,
-        "ModernMigrate⭐": 8192,
-        "RetroRecode🔄": 4096
-    }
-    
-    # Calculate available tokens for new content
-    input_tokens = len(formatted_text.split())
-    max_new_tokens = max_tokens[selected_model] - input_tokens
-    
-    # Ensure max_new_tokens is within the model's limit
-    if selected_model == "RetroRecode🔄":
-        max_new_tokens = min(max_new_tokens, 3000)
-    
+    max_new_tokens = 3000
+    if selected_model != "RetroRecode🔄":
+        input_tokens = len(formatted_text.split())
+        max_tokens = {"LegacyLift🚀": 32000, "ModernMigrate⭐": 8192}
+        max_new_tokens = max_tokens[selected_model] - input_tokens
+
     with st.chat_message("assistant"):
-        client = InferenceClient(
-            model=model_links[selected_model], )
+        client = InferenceClient(model=model_links[selected_model])
         output = client.text_generation(
             formatted_text,
-            temperature=temp_values,  # 0.5
+            temperature=temp_values,
             max_new_tokens=max_new_tokens,
             stream=True
         )