Skip to content

Instantly share code, notes, and snippets.

View FuRuF-11's full-sized avatar
💭
I may be slow to respond.

FURUF FuRuF-11

💭
I may be slow to respond.
View GitHub Profile
@willccbb
willccbb / grpo_demo.py
Last active November 11, 2025 18:51
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},