import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_name = "your-username/your-model-name"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)

def chat_fn(user_input, history=[]):
    # Build full chat context
    conversation = ""
    for u, r in history:
        conversation += f"User: {u}\nBot: {r}\n"
    conversation += f"User: {user_input}\nBot:"

    inputs = tokenizer(conversation, return_tensors="pt").to(device)
    outputs = model.generate(**inputs, max_length=500, pad_token_id=tokenizer.eos_token_id)
    response = tokenizer.decode(outputs[0], skip_special_tokens=True).split("Bot:")[-1].strip()

    history.append((user_input, response))
    return history, history

iface = gr.ChatInterface(fn=chat_fn, title="Awesome's Chatbot")
iface.launch()