willccbb

# train_grpo.py
#
# See https://github.com/willccbb/verifiers for ongoing developments
#
import re
import torch
from datasets import load_dataset, Dataset
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import LoraConfig
from trl import GRPOConfig, GRPOTrainer

veekaybee

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

veekaybee

ChatGPT Resources

Context

ChatGPT appeared like an explosion on all my social media timelines in early December 2022. While I keep up with machine learning as an industry, I wasn't focused so much on this particular corner, and all the screenshots seemed like they came out of nowhere. What was this model? How did the chat prompting work? What was the context of OpenAI doing this work and collecting my prompts for training data?

I decided to do a quick investigation. Here's all the information I've found so far. I'm aggregating and synthesizing it as I go, so it's currently changing pretty frequently.

Model Architecture

ih2502mk

Lecture 1: Introduction to Research — [📝Lecture Notebooks] [▶️Video]
Lecture 2: Introduction to Python — [📝Lecture Notebooks] [▶️Video]
Lecture 3: Introduction to NumPy — [📝Lecture Notebooks] [▶️Video]
Lecture 4: Introduction to pandas — [📝Lecture Notebooks] [▶️Video]
Lecture 5: Plotting Data — [📝Lecture Notebooks] [[▶️Vide

elizarov

import kotlin.coroutines.*
import kotlin.coroutines.intrinsics.*

/**
 * Implementation for Delimited Continuations `shift`/`reset` primitives via Kotlin Coroutines.
 * See [https://en.wikipedia.org/wiki/Delimited_continuation].
 *
 * The following LISP code:
 *
 * ```

johnmcase

rem see https://github.com/coreybutler/nvm-windows/issues/300

@echo off
SETLOCAL EnableDelayedExpansion

if [%1] == [] (
	echo Pass in the version you would like to install, or "latest" to install the latest npm version.
) else (
	set wanted_version=%1

MohamedAlaa

tmux shortcuts & cheatsheet

start new:

tmux

start new with session name:

tmux new -s myname

sebfisch

Delimited Continuations

Delimited continuations manipulate the control flow of programs. Similar to control structures like conditionals or loops they allow to deviate from a sequential flow of control.

We use exception handling as another example for control flow manipulation and later show how to implement it using delimited continuations. Finally, we show that nondeterminism can also be expressed using delimited continuations.

Exception Handling