import os
#os.system('git clone https://github.com/tloen/alpaca-lora.git')
import streamlit as st
from streamlit_chat import message as st_message
import bitsandbytes as bnb
from transformers import GenerationConfig
from transformers import AutoTokenizer, AutoConfig, LlamaForCausalLM, LlamaTokenizer

tokenizer = LlamaTokenizer.from_pretrained("wxjiao/alpaca-7b")

model2 = LlamaForCausalLM.from_pretrained(
    "wxjiao/alpaca-7b",
    load_in_8bit_fp32_cpu_offload=True,
    from_pretrained="auto",
)