Update app.py

app.py

@@ -1,70 +1,35 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-import spaces
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from spaces import GPU
+
+model_name = "microsoft/DialoGPT-small"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model.to(device)
+
+@GPU
+def generate_response(message, history):
+    input_ids = tokenizer.encode(message + tokenizer.eos_token, return_tensors="pt").to(device)
+    chat_history_ids = input_ids
+    response_ids = model.generate(
+        chat_history_ids,
+        max_length=200,
+        pad_token_id=tokenizer.eos_token_id,
+        do_sample=True,
+        temperature=0.7
+    )
+    response = tokenizer.decode(response_ids[:, chat_history_ids.shape[-1]:][0], skip_special_tokens=True)
+    return response.strip()
 
-@spaces.GPU
-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="sapientinc/HRM-Text-1B")
-
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
-
-    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,
-    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)",
-        ),
-    ],
+    fn=generate_response,
+    title="Simple ZeroGPU Chatbot",
+    description="A simple chatbot using DialoGPT, running on Hugging Face ZeroGPU.",
+    examples=["Hello!", "How are you today?", "What's the latest news?"]
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
-
 if __name__ == "__main__":
-    demo.launch()
+    chatbot.launch()