# Import necessary libraries
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Load the tokenizer and model
tokenizer = AutoTokenizer.from_pretrained("chuanli11/Llama-3.2-3B-Instruct-uncensored")
model = AutoModelForCausalLM.from_pretrained("chuanli11/Llama-3.2-3B-Instruct-uncensored")

def generate_response(input_text):
    # Encode the input text and generate response
    inputs = tokenizer(input_text, return_tensors="pt")
    outputs = model.generate(**inputs, max_length=150, do_sample=True, temperature=0.7, top_p=0.9)
    
    # Decode the output to get the chatbot response
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return response

def chat():
    print("Chatbot: Hello! I'm here to assist you. Type 'exit' to end the conversation.")
    while True:
        user_input = input("You: ")
        if user_input.lower() == "exit":
            print("Chatbot: Goodbye!")
            break

        # Generate the response from the chatbot
        response = generate_response(user_input)
        print(f"Chatbot: {response}")

# Start the chat
if __name__ == "__main__":
    chat()