Skip to content

Instantly share code, notes, and snippets.

View beyonddream's full-sized avatar
🎯
A thinking gradient descent

Arun beyonddream

🎯
A thinking gradient descent
View GitHub Profile
@beyonddream
beyonddream / grpo_demo.py
Created July 18, 2026 20:09 — forked from willccbb/grpo_demo.py
GRPO Llama-1B
# 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},
import time
import zlib
from threading import Lock, Thread
class Metric(object):
def add(self, value):
raise NotImplementedError()
def flush(self):
@beyonddream
beyonddream / microgpt.py
Created February 13, 2026 21:56 — forked from karpathy/microgpt.py
microgpt
"""
The most atomic way to train and inference a GPT in pure, dependency-free Python.
This file is the complete algorithm.
Everything else is just efficiency.
@karpathy
"""
import os # os.path.exists
import math # math.log, math.exp
@beyonddream
beyonddream / tmux.md
Created January 29, 2026 05:58 — forked from andreyvit/tmux.md
tmux cheatsheet

tmux cheat sheet

(C-x means ctrl+x, M-x means alt+x)

Prefix key

The default prefix is C-b. If you (or your muscle memory) prefer C-a, you need to add this to ~/.tmux.conf:

remap prefix to Control + a