Skip to content

Instantly share code, notes, and snippets.

View aryamanan's full-sized avatar
💭
I may be slow to respond.

Aryan Arora aryamanan

💭
I may be slow to respond.
View GitHub Profile
class SimpleAdam(torch.optim.Optimizer):
def __init__(self, params, lr=1e-3, betas=(0.9, 0.999), eps=1e-8):
super().__init__(params, defaults={'lr': lr})
self.state = {}
self.t = 0
self.betas = betas
self.eps = eps
for group in self.param_groups:
for p in group['params']:
@willccbb
willccbb / grpo_demo.py
Last active October 25, 2025 16:39
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},
@sineto
sineto / App.js
Last active February 18, 2025 15:36
User Authentication with Context API and Hooks (useContext, useState)
import React from 'react';
import { BrowserRouter } from 'react-router-dom';
import { UserProvider } from './services/UserContext';
import Routes from './Routes'
function App() {
return (
<BrowserRouter>