Update app.py

app.py

@@ -3,32 +3,34 @@ from huggingface_hub import InferenceClient
 
 client = InferenceClient("Futuresony/future_ai_12_10_2024.gguf")
 
-def respond(message, history, system_message, max_tokens, temperature, top_p):
-    messages = [{"role": "system", "content": system_message}]
+def format_alpaca_prompt(user_input, system_prompt):
+    """Formats input in Alpaca/LLaMA style"""
+    prompt = f"""{system_prompt}
+
+### Instruction:
+{user_input}
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+### Response:
+"""
+    return prompt
 
-    messages.append({"role": "user", "content": message})
+def respond(message, history, system_message, max_tokens, temperature, top_p):
+    formatted_prompt = format_alpaca_prompt(message, system_message)
 
-    response = client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
+    response = client.text_generation(
+        formatted_prompt,  # ✅ Pass as a single string
+        max_new_tokens=max_tokens,  # ✅ Use max_new_tokens, not max_tokens
         temperature=temperature,
         top_p=top_p,
     )
 
-    response_text = response["choices"][0]["message"]["content"]
-    yield response_text  # Output full response
+    yield response  # ✅ Output the generated response
 
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
+        gr.Slider(minimum=1, maximum=250, value=128, step=1, label="Max new tokens"),  # ✅ Keep ≤250
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
     ],