app.py

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

model_id = "openchat/openchat-3.5-1210"

# Load model
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    torch_dtype=torch.float16
)

# System prompt
def build_prompt(history, user_input):
    system_prompt = "<|system|>\nYou are a helpful AI assistant.\n"
    messages = system_prompt

    for user, bot in history:
        messages += f"<|user|>\n{user}\n<|assistant|>\n{bot}\n"
    messages += f"<|user|>\n{user_input}\n<|assistant|>\n"
    return messages

def chat(user_input, history=[]):
    prompt = build_prompt(history, user_input)
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

    output = model.generate(
        **inputs,
        max_new_tokens=300,
        temperature=0.7,
        do_sample=True,
        top_p=0.9,
        pad_token_id=tokenizer.eos_token_id
    )

    response = tokenizer.decode(output[0], skip_special_tokens=True)
    answer = response.split("<|assistant|>")[-1].strip()
    history.append((user_input, answer))
    return answer, history

gr.ChatInterface(chat, title="OpenChat AI Assistant").launch()