Update app.py

app.py

@@ -1,70 +1,31 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
 
+model_name = "Qwen/Qwen2.5-Coder-1.5B-Instruct"
 
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    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="openai/gpt-oss-20b")
-
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto"
+)
 
+def respond(message, history):
+    messages = []
+    for user, bot in history:
+        messages.append({"role": "user", "content": user})
+        messages.append({"role": "assistant", "content": bot})
     messages.append({"role": "user", "content": message})
 
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        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
-
-
-"""
-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.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(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
+    text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
+    generated_ids = model.generate(**model_inputs, max_new_tokens=512)
+    output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist()
+    content = tokenizer.decode(output_ids, skip_special_tokens=True)
 
+    return content
 
-if __name__ == "__main__":
-    demo.launch()
+demo = gr.ChatInterface(respond)
+demo.launch()