Create app.py

app.py

@@ -1,64 +1,31 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
 
-"""
-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("HuggingFaceH4/zephyr-7b-beta")
+tokenizer = AutoTokenizer.from_pretrained("gpt2")
+model = AutoModelForCausalLM.from_pretrained("gpt2")
 
+def respond(message, chat_history):
+    # Append user message to chat history
+    chat_history = chat_history or []
+    chat_history.append(message)
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+    # Prepare input (concatenate previous chat for context)
+    input_text = " ".join(chat_history)
+    input_ids = tokenizer.encode(input_text + tokenizer.eos_token, return_tensors='pt')
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+    # Generate response
+    output_ids = model.generate(input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id)
+    output_text = tokenizer.decode(output_ids[:, input_ids.shape[-1]:][0], skip_special_tokens=True)
 
-    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,
-    ):
-        token = message.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
-"""
-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=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)",
-        ),
-    ],
-)
+    chat_history.append(output_text)
+    return output_text, chat_history
 
+with gr.Blocks() as demo:
+    chat_history = gr.State([])
+    chatbot = gr.Chatbot()
+    msg = gr.Textbox(placeholder="Ask me anything...")
+    msg.submit(respond, [msg, chat_history], [chatbot, chat_history])
 
 if __name__ == "__main__":
     demo.launch()