Peter pszemraj

whistleblowing_ai.md

Whistleblowing within AI companies, especially concerning sensitive information like model sizes and training methods, is a significant and serious action. It requires careful consideration of the legal, ethical, and personal implications involved. This guide aims to provide employees with comprehensive information on safely and anonymously whistleblowing or leaking confidential AI-related data while minimizing personal and professional risks.

	import logging
	import os

	import fire
	import torch
	from datasets import load_dataset
	from huggingface_hub import PyTorchModelHubMixin
	from torch import nn
	from transformers import AutoConfig, AutoModel, AutoTokenizer

	# !pip install -q sentence-splitter
	import os
	from sentence_splitter import split_text_into_sentences

	REFUSAL_TERMS = [
	"sorry",
	"i can't",
	"unfortunately,",
	"as a language model",
	"as an ai language model",

	import re


	def extract_comments_and_docs(multiline_string):
	# Pattern to match lines where the first non-whitespace character is '#'

	comment_pattern = r"^\s#(.)"

	# Pattern to match any text within triple quotes (either ''' or """)

	import boto3
	import gzip
	from datasets import load_dataset
	from botocore import UNSIGNED
	from botocore.config import Config

	num_proc = 32
	s3 = boto3.client("s3", config=Config(signature_version=UNSIGNED))

	bucket_name = "softwareheritage"

	import logging
	import os

	import fire
	import torch
	from datasets import load_dataset
	from huggingface_hub import PyTorchModelHubMixin
	from torch import nn
	from transformers import AutoConfig, AutoModel, AutoTokenizer

	import base64
	import os
	from pathlib import Path

	import fire
	from openai import OpenAI
	from tqdm.auto import tqdm
	from joblib import Memory

	# Set up joblib caching

	import streamlit as st
	import pandas as pd
	from datasets import load_from_disk
	import textwrap
	import json

	# Constants
	ROWS_PER_PAGE = 100
	LOGO_URL = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/datasets/datasets_logo.png"
	DOCS_URL = "https://huggingface.co/docs/datasets/index"

	"""
	parses the standard main.log from nanoT5 and makes some plots

	pip install matplotlib pandas seaborn
	"""
	import argparse
	import logging
	import os
	import re
	from pathlib import Path

Peter pszemraj

whistleblowing_ai.md

Table of Contents