app.py

# main.py
import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline

# Load model and tokenizer
model_name = "meta-llama/Llama-2-7b-chat-hf"
model = AutoModelForCausalLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)
chat_pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer)

# Define the generate_response function
def generate_response(prompt):
    response = chat_pipeline(prompt, max_length=50)[0]['generated_text']
    return response

# Create Gradio interface
interface = gr.Interface(
    fn=generate_response,
    inputs="text",
    outputs="text",
    layout="vertical",
    title="LLAMA-2-7B Chatbot",
    description="Enter a prompt and get a chatbot response.",
    examples=[["Tell me a joke."]],
)

if __name__ == "__main__":
    interface.launch()