Skip to content

Instantly share code, notes, and snippets.

View yanghh2000's full-sized avatar

haihui yang yanghh2000

View GitHub Profile
@willccbb
willccbb / grpo_demo.py
Last active November 14, 2025 14:40
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},