Skip to content

Instantly share code, notes, and snippets.

View bishesh16's full-sized avatar

Bishesh Adhikari bishesh16

  • Amazon Web Services
  • London, UK
View GitHub Profile
# train_grpo.py
from typing import *
import re
import torch
from datasets import load_dataset, Dataset, load_from_disk
from transformers import AutoTokenizer, AutoModelForCausalLM, TrainingArguments
from peft import LoraConfig
from trl import GRPOConfig, GRPOTrainer, TrlParser
from dataclasses import dataclass, field
@willccbb
willccbb / grpo_demo.py
Last active November 2, 2025 13:27
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},
pragma solidity ^0.4.18;
/**
* @title Ownable
* @dev The Ownable contract has an owner address, and provides basic authorization control
* functions, this simplifies the implementation of "user permissions".
* @author https://github.com/OpenZeppelin/zeppelin-solidity
*/
contract Ownable {
@persiyanov
persiyanov / howto.md
Last active October 21, 2021 15:35
How-to get Amazon EC2 instance and do machine learning on it. Jupyter 4.0.6 server and Python 2.7.

Goal

Want to move computation on machine with much power. We will set up Anaconda 4.0.0 and XGBoost 0.4 (it is tricky installable).

Preliminaries

Let's start

AWS Console and launching EC2 Instance.

@aaronhoffman
aaronhoffman / aws-sns-event-template-with-actual-ses-deliverynotification-sns-message
Last active January 15, 2019 19:04
Lambda function to process a Amazon SES Delivery Notification message from a SNS Topic into a DynamoDB Table
{
"Records": [
{
"EventSource":"aws:sns",
"EventVersion":"1.0",
"EventSubscriptionArn":"arn:aws:sns:us-west-2:xxxx:xxxx",
"Sns": {
"Type":"Notification",
"MessageId":"88B1B251-2E92-4FC3-BFAA-E3BBD0BAB10A",
"TopicArn":"arn:aws:sns:us-west-2:881222951025:survey-tool-ses-delivery",
@markusklems
markusklems / lambda-dynamo
Last active November 24, 2024 01:48
Short aws lambda sample program that puts an item into dynamodb
// create an IAM Lambda role with access to dynamodb
// Launch Lambda in the same region as your dynamodb region
// (here: us-east-1)
// dynamodb table with hash key = user and range key = datetime
console.log('Loading event');
var AWS = require('aws-sdk');
var dynamodb = new AWS.DynamoDB({apiVersion: '2012-08-10'});
exports.handler = function(event, context) {