Update app.py

app.py

@@ -1,49 +1,42 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 
+MODEL_NAME = "basmala12/smollm_finetuning5"
 
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
-    """
-    Updated to use your fine-tuned model:
-    basmala12/smollm_finetuning5
-    """
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+model = AutoModelForCausalLM.from_pretrained(MODEL_NAME)
 
-    # Load your fine-tuned model through HF Inference API
-    client = InferenceClient(
-        token=hf_token.token,
-        model="basmala12/smollm_finetuning5"     # <- your model
-    )
+pipe = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    max_new_tokens=200,
+)
 
-    # Build chat messages
+def respond(message, history, system_message, max_tokens, temperature, top_p):
     messages = [{"role": "system", "content": system_message}]
     messages.extend(history)
     messages.append({"role": "user", "content": message})
 
-    response = ""
-
-    # Streaming response from HF Inference API
-    for msg in client.chat_completion(
+    prompt = tokenizer.apply_chat_template(
         messages,
-        max_tokens=max_tokens,
-        stream=True,
+        tokenize=False,
+        add_generation_prompt=True
+    )
+
+    output = pipe(
+        prompt,
+        max_new_tokens=max_tokens,
         temperature=temperature,
         top_p=top_p,
-    ):
-        choices = msg.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
+        do_sample=True
+    )[0]["generated_text"]
+
+    # Extract assistant response
+    answer = output.split("<|im_start|>assistant")[-1]
+    answer = answer.replace("<|im_end|>", "").strip()
 
-        response += token
-        yield response
+    return answer
 
 
 chatbot = gr.ChatInterface(
@@ -52,19 +45,17 @@ chatbot = gr.ChatInterface(
     additional_inputs=[
         gr.Textbox(
             value="Give short answers with brief logical reasoning.",
-            label="System message"
+            label="System Message"
         ),
-        gr.Slider(minimum=1, maximum=2048, value=256, step=1, label="Max new tokens"),
-        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=0.9, step=0.05, label="Top-p"),
+        gr.Slider(1, 1024, value=256, step=1, label="Max new tokens"),
+        gr.Slider(0.1, 4.0, value=0.7, step=0.1, label="Temperature"),
+        gr.Slider(0.1, 1.0, value=0.9, step=0.05, label="Top-p"),
     ],
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()  # user logs in with their HF account (required for private models)
+demo = gr.Blocks()
+with demo:
     chatbot.render()
 
-
 if __name__ == "__main__":
     demo.launch()