FoobarProtocol

#!/usr/bin/env python3

import json
import openai
import time
import os
import logging
from openai.error import InvalidRequestError, RateLimitError
from concurrent.futures import ThreadPoolExecutor

FoobarProtocol

import argparse
import os

import torch
from accelerate import Accelerator
from datasets import load_dataset
from peft import LoraConfig, get_peft_model, prepare_model_for_int8_training, set_peft_model_state_dict
from torch.utils.data import IterableDataset
from tqdm import tqdm
from transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer, Trainer, TrainingArguments, logging, set_seed

FoobarProtocol

import argparse
import csv
import os

# Function to calculate total rows in CSV
def get_total_rows(csv_file):
    with open(csv_file, 'r') as f:
        return sum(1 for row in csv.reader(f)) - 1  # Exclude header

# Function to split CSV files

FoobarProtocol

# Importing necessary libraries for data preprocessing and visualization
import matplotlib.pyplot as plt
import numpy as np
from tqdm.notebook import trange
import pandas as pd
import random
import torch
import re
from datasets import load_dataset
from simplet5 import SimpleT5

FoobarProtocol

import os
import logging
import csv
import argparse
from tqdm import tqdm
import sys
from dotenv import load_dotenv
import openai

logging.basicConfig(level=logging.INFO,

FoobarProtocol

def convert_alpaca_to_evol(
    file_path: str, 
    lines: bool = False,
    output_file: str = "converted_alpaca.json"
):
    """Convert the Instruction/Input/Output format of Alpaca Instruct datasets
    to the Evol-Instruct format of Instruction/Output. Inputs are appended to the
    instructions.
    
    Args:

FoobarProtocol

import json
import random

from openai_access import call_chatgpt
from depth import createConstraintsPrompt, createDeepenPrompt, createConcretizingPrompt, createReasoningPrompt
from breadth import createBreadthPrompt


fr = open('alpaca_data.json','r')

FoobarProtocol

import re
import json
import uuid
inputs = [json.loads(line) for line in open("instructions.jsonl").readlines()]

def split_response(instruction, response):
    if '</s>' not in response:
        return [
            {
                "from": "human",

FoobarProtocol

import openai

api_keys = ['api-key-1', 'api-key-2', 'api-key-3']  # Replace with your actual API keys
num_prompts = 1000
prompts_per_request = 100  # Adjust based on your needs
num_requests = 10

prompts = []

for i in range(num_requests):

FoobarProtocol

from transformers import AutoTokenizer, BitsAndBytesConfig, AutoModelForSeq2SeqLM

model_id = "google/flan-t5-xxl"

quantization_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_use_double_quant=False
)

model = AutoModelForSeq2SeqLM.from_pretrained(model_id, quantization_config=quantization_config)