Rewrite with transformers

app.py

@@ -1,7 +1,15 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
-SYSTEM_PROMPT = """"""
+MODEL_ID = "le-llm/gemma-3-12b-it-reasoning"
+
+# Load model & tokenizer
+device = "cuda" if torch.cuda.is_available() else "cpu"
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
+model = AutoModelForCausalLM.from_pretrained(MODEL_ID, torch_dtype=torch.float16 if device=="cuda" else torch.float32).to(device)
+
+SYSTEM_PROMPT = "You are a friendly Chatbot."
 
 def respond(
     message,
@@ -10,45 +18,32 @@ def respond(
     max_tokens,
     temperature,
     top_p,
-    hf_token: gr.OAuthToken,
 ):
-    """
-    For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-    """
-    client = InferenceClient(token=hf_token.token, model="le-llm/gemma-3-12b-it-reasoning")
-
-    messages = [{"role": "system", "content": system_message}]
 
-    messages.extend(history)
+    conversation = system_message + "\n"
+    for turn in history:
+        role = "User" if turn["role"] == "user" else "Assistant"
+        conversation += f"{role}: {turn['content']}\n"
+    conversation += f"User: {message}\nAssistant:"
 
-    messages.append({"role": "user", "content": message})
+    inputs = tokenizer(conversation, return_tensors="pt").to(device)
 
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
+    output_ids = model.generate(
+        **inputs,
+        max_new_tokens=max_tokens,
         temperature=temperature,
         top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
-
-        response += token
-        yield response
+        do_sample=True,
+    )
 
+    response = tokenizer.decode(output_ids[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)
+    yield response
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
 chatbot = gr.ChatInterface(
     respond,
     type="messages",
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Textbox(value=SYSTEM_PROMPT, label="System message"),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(
@@ -64,6 +59,5 @@ chatbot = gr.ChatInterface(
 with gr.Blocks() as demo:
     chatbot.render()
 
-
 if __name__ == "__main__":
     demo.launch()