app.py

# import dependencies
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, pipeline

import os
import gradio as gr
#from google.colab import drive

import chromadb
from langchain.llms import HuggingFacePipeline
from langchain.document_loaders import TextLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.vectorstores import Chroma
from langchain import HuggingFacePipeline
from langchain.document_loaders import PyPDFDirectoryLoader
from langchain.chains import ConversationalRetrievalChain
from langchain.memory import ConversationBufferMemory

# specify model huggingface mode name
model_name = "anakin87/zephyr-7b-alpha-sharded"
#https://huggingface.co/anakin87/zephyr-7b-alpha-sharded

#HuggingFaceH4/zephyr-7b-alpha
#https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha

# function for loading 4-bit quantized model
def load_quantized_model(model_name: str):
    """
    :param model_name: Name or path of the model to be loaded.
    :return: Loaded quantized model.
    """
    bnb_config = BitsAndBytesConfig(
        load_in_4bit=True,
        bnb_4bit_use_double_quant=True,
        bnb_4bit_quant_type="nf4",
        bnb_4bit_compute_dtype=torch.bfloat16
    )

    model = AutoModelForCausalLM.from_pretrained(
        model_name,
        load_in_4bit=True,
        torch_dtype=torch.bfloat16,
        quantization_config=bnb_config
    )
    return model

# fucntion for initializing tokenizer
def initialize_tokenizer(model_name: str):
    """
    Initialize the tokenizer with the specified model_name.

    :param model_name: Name or path of the model for tokenizer initialization.
    :return: Initialized tokenizer.
    """
    tokenizer = AutoTokenizer.from_pretrained(model_name)
    tokenizer.bos_token_id = 1  # Set beginning of sentence token id
    return tokenizer

# load model
model = load_quantized_model(model_name)

# initialize tokenizer
tokenizer = initialize_tokenizer(model_name)

# specify stop token ids
stop_token_ids = [0]