Update app.py

app.py

@@ -29,7 +29,7 @@ model_info = {
     },
 }
 
-def format_promt(message, conversation_history, custom_instructions=None):
+def format_prompt(message, conversation_history, custom_instructions=None):
     prompt = ""
     if custom_instructions:
         prompt += f"\[INST\] {custom_instructions} \[/INST\]"
@@ -104,7 +104,7 @@ if prompt := st.chat_input(f"Hi I'm {selected_model}, How can I help you today?"
     st.session_state.messages.append({"role": "user", "content": prompt})
     conversation_history = [(message["role"], message["content"]) for message in st.session_state.messages]
     
-    formated_text = format_promt(prompt, conversation_history, custom_instruction)
+    formatted_text = format_prompt(prompt, conversation_history, custom_instruction)
     
     max_tokens = {
         "LegacyLift🚀": 32000,
@@ -113,14 +113,18 @@ if prompt := st.chat_input(f"Hi I'm {selected_model}, How can I help you today?"
     }
     
     # Calculate available tokens for new content
-    input_tokens = len(formated_text.split())
-    max_new_tokens = max(0, max_tokens[selected_model] - input_tokens)
+    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)
     
     with st.chat_message("assistant"):
         client = InferenceClient(
             model=model_links[selected_model], )
         output = client.text_generation(
-            formated_text,
+            formatted_text,
             temperature=temp_values,  # 0.5
             max_new_tokens=max_new_tokens,
             stream=True