# -*- coding: utf-8 -*-
"""
Created on Sat Oct  5 16:41:22 2024

@author: Admin
"""

import gradio as gr
from transformers import pipeline
import os
from huggingface_hub import login
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch


#chatbot = pipeline(model="NCSOFT/Llama-3-OffsetBias-8B")
#token = os.getenv("HF_TOKEN")
login(token = os.getenv('HF_TOKEN'))
#chatbot = pipeline(model="meta-llama/Llama-3.2-1B")

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.2-1B-Instruct")
model = AutoModelForCausalLM.from_pretrained(
    "meta-llama/Llama-3.2-1B-Instruct",
    device_map="auto",
    torch_dtype="auto",
)

#chatbot = pipeline(model="facebook/blenderbot-400M-distill")

message_list = []
response_list = []


def vanilla_chatbot(message, history):
    inputs = tokenizer(message, return_tensors="pt").to("cpu")
    with torch.no_grad():
        outputs = model.generate(inputs.input_ids, max_length=100)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)
    #conversation = chatbot(message)
    
    #return conversation[0]['generated_text']

demo_chatbot = gr.ChatInterface(vanilla_chatbot, title="Vanilla Chatbot", description="Enter text to start chatting.")

demo_chatbot.launch(True)