s3nh s3nh

Anti-hype LLM reading list

Goals: Add links that are reasonable and good explanations of how stuff works. No hype and no vendor content if possible. Practical first-hand accounts of models in prod eagerly sought.

Foundational Concepts

Pre-Transformer Models

Risk Assessment of GitHub Copilot

0xabad1dea, July 2021

this is a rough draft and may be updated with more examples

GitHub was kind enough to grant me swift access to the Copilot test phase despite me @'ing them several hundred times about ICE. I would like to examine it not in terms of productivity, but security. How risky is it to allow an AI to write some or all of your code?

Ultimately, a human being must take responsibility for every line of code that is committed. AI should not be used for "responsibility washing." However, Copilot is a tool, and workers need their tools to be reliable. A carpenter doesn't have to

	# train_grpo.py
	#
	# See https://github.com/willccbb/verifiers for ongoing developments
	#
	"""
	citation:

	@misc{brown2025grpodemo,
	title={Granular Format Rewards for Eliciting Mathematical Reasoning Capabilities in Small Language Models},
	author={Brown, William},

	from typing import List, Dict, Literal, Union
	from transformers import AutoTokenizer


	class MistralAICtx:

	def __init__(self, model_name: str):
	assert "mistral" in model_name, "MistralCtx only available for Mistral models"
	self.tokenizer = AutoTokenizer.from_pretrained(
	"mistralai/Mistral-7B-Instruct-v0.2")

	import torch
	from unsloth import FastLlamaModel
	from transformers import TrainingArguments
	from datasets import load_dataset
	from trl import DPOTrainer

	model_name = "teknium/OpenHermes-2.5-Mistral-7B"
	model_name = "./OpenHermes-2.5-Mistral-7B"
	new_model = "NeuralHermes-2.5-Mistral-7B"

	import torch
	from typing import Optional
	from flash_attn import flash_attn_func, flash_attn_qkvpacked_func
	from diffusers.models.attention import Attention

	class FlashAttnProcessor:
	r"""
	Processor for implementing memory efficient attention using flash_attn.
	"""

	import torch

	from pipe import StableDiffusionXLPipelineNoWatermark
	from pipei2i import StableDiffusionXLImg2ImgPipelineNoWatermark
	from diffusers import DiffusionPipeline
	from PIL import Image
	import os
	import gc
	import pandas as pd
	import random, sys

	import os
	import sys
	from typing import List

	import fire
	import torch
	import transformers
	from datasets import load_dataset, DatasetDict
	from transformers import Seq2SeqTrainer, TrainerCallback, TrainingArguments, TrainerState, TrainerControl
	from transformers.trainer_utils import PREFIX_CHECKPOINT_DIR

	add_executable(infervideo infervideo.cpp)
	target_link_libraries(infervideo PRIVATE retinanet ${OpenCV_LIBS} cuda ${CUDA_LIBRARIES})