app.py

import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "meta-llama/Meta-Llama-3-8B"
model = AutoModelForCausalLM.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

def generate_response(input_text):
    inputs = tokenizer(input_text, return_tensors="pt")
    outputs = model.generate(**inputs, max_length=100)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

interface = gr.Interface(
    fn=generate_response,
    inputs="text",
    outputs="text",
    title="Chatbot",
    description="Enter your text to get a response from the LLaMA model.",
)

interface.launch()