app.py

# Import libraries
import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load model and tokenizer
model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-70b-chat-hf")
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-2-70b-chat-hf")

# Define a function to generate responses
def chatbot(text):
# Encode the input text
input_ids = tokenizer.encode(text + tokenizer.eos_token, return_tensors="pt")
# Generate a response
output_ids = model.generate(input_ids, max_length=1000, pad_token_id=tokenizer.eos_token_id)
# Decode the output
output_text = tokenizer.decode(output_ids[0], skip_special_tokens=True)
# Return the output text
return output_text

# Create a web interface
iface = gr.Interface(chatbot, "textbox", "text", examples=[["Hello"], ["How are you?"], ["What is your name?"]])
# Launch the interface
iface.launch()