oxillix

Ask the right question; Get the right answer

oxillix / grpo_demo.py

Created February 13, 2025 22:58 — forked from willccbb/grpo_demo.py

GRPO Llama-1B

	# train_grpo.py
	import re
	import torch
	from datasets import load_dataset, Dataset
	from transformers import AutoTokenizer, AutoModelForCausalLM
	from peft import LoraConfig
	from trl import GRPOConfig, GRPOTrainer

	# Load and prep dataset

oxillix / autoSpotifyPause.py

Created March 16, 2021 18:28

Auto-stopping Spotify while other programs play audio | auto pause spotify when another source starts playing

	#!/usr/bin/env python

	# pip install dbus-python pulsectl

	import signal
	import sys
	import pulsectl
	import dbus

	def sig_handler(signal, frame):