Skip to content

Instantly share code, notes, and snippets.

View johnnydevriese's full-sized avatar

Johnny Devriese johnnydevriese

View GitHub Profile
@johnnydevriese
johnnydevriese / llm_grpo.py
Created September 26, 2025 16:47
train an LLM using GRPO
import re
import torch
import verifiers as vf
from datasets import Dataset, load_dataset
from peft import LoraConfig
from transformers import AutoModelForCausalLM, AutoTokenizer
# ---------------------------------------------------------------------------
# Data Loading and Preparation
use std::env;
use std::error::Error;
use std::fs::File;
use std::io::{BufReader, Read};
use std::path::Path;
use std::process;
const NUM_TOKENS: usize = 27;
const EOT_TOKEN: usize = 0;
@johnnydevriese
johnnydevriese / install_dev.sh
Last active March 7, 2024 21:46
packages to install
#! /bin/bash
brew update
echo "install arc browser"
brew install --cask arc
echo "install chrome"
brew install --cask google-chrome
@johnnydevriese
johnnydevriese / .bash_profile
Created March 1, 2018 15:26 — forked from natelandau/.bash_profile
Mac OSX Bash Profile
# ---------------------------------------------------------------------------
#
# Description: This file holds all my BASH configurations and aliases
#
# Sections:
# 1. Environment Configuration
# 2. Make Terminal Better (remapping defaults and adding functionality)
# 3. File and Folder Management
# 4. Searching
# 5. Process Management