app.py

import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer

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

# Set pad token
tokenizer.pad_token = tokenizer.eos_token

# Define chatbot function
def chat(user_input):
    inputs = tokenizer(user_input, return_tensors="pt", padding=True)
    output = model.generate(inputs.input_ids, max_length=128, do_sample=True, temperature=0.6)
    return tokenizer.decode(output[0], skip_special_tokens=True)

# Create Gradio UI
iface = gr.Interface(fn=chat, inputs="text", outputs="text", title="Llama 2 Chatbot")
iface.launch()