Skip to content

Instantly share code, notes, and snippets.

@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},
$subscriptionId = "xxx"
$resourceGroup = "xxx"
$azfwPolicyName = "xxx"
function GetIpGroupName {
param ( [string] $resourceId )
$resourceSubscriptionId = (Get-AzResource -ResourceId $resourceId).SubscriptionId
$context = Get-AzContext