app.py

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

# Load model and tokenizer
model_name = "meta-llama/Llama-2-7b-chat-hf"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")

def generate_response(message, history):
    # Format the input with chat history
    prompt = "".join([f"Human: {h[0]}\nAssistant: {h[1]}\n" for h in history])
    prompt += f"Human: {message}\nAssistant:"

    # Tokenize and generate
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
    outputs = model.generate(**inputs, max_new_tokens=1000, temperature=0.7, do_sample=True)
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)

    # Extract only the assistant's response
    assistant_response = response.split("Assistant:")[-1].strip()
    return assistant_response

# Create the Gradio interface
iface = gr.ChatInterface(
    generate_response,
    title="Llama-2-7b Chat Interface",
    description="Chat with the Llama-2-7b model. Type your message and press Enter.",
    examples=[
        "What is the capital of France?",
        "Explain quantum computing in simple terms.",
        "Write a short poem about artificial intelligence."
    ],
    cache_examples=False,
)

# Launch the interface
iface.launch()