Tagged articles

GSM8K

3 articles · Page 1 of 1

Aug 2, 2026 · Artificial Intelligence

Building a From‑Scratch LLM Training Framework: Full GRPO vs PPO vs DPO Comparison on GSM8K

The article presents a from‑scratch LLM training framework called grpo‑llm, implements GRPO with Trio rollout, FSDP and a C++ reward extension, and conducts a controlled experiment comparing GRPO, PPO and DPO on the GSM8K math‑reasoning benchmark, revealing why DPO outperforms the other two under sparse binary rewards.

DPOGRPOGSM8K

0 likes · 10 min read

Building a From‑Scratch LLM Training Framework: Full GRPO vs PPO vs DPO Comparison on GSM8K

PaperAgent

Feb 7, 2026 · Artificial Intelligence

Can 13 Parameters Match Full‑Scale Fine‑Tuning? TinyLoRA’s RL Breakthrough

TinyLoRA, a Meta‑proposed method that fine‑tunes Qwen2.5‑7B with only 13 trainable parameters (26 bytes), achieves 91% accuracy on GSM8K under reinforcement learning, revealing that ultra‑low‑parameter RL can rival full‑scale supervised fine‑tuning.

GSM8KQwen2.5TinyLoRA

0 likes · 7 min read

Can 13 Parameters Match Full‑Scale Fine‑Tuning? TinyLoRA’s RL Breakthrough

Fun with Large Models

Jun 12, 2025 · Artificial Intelligence

Implement GRPO to Give LLMs Reasoning Ability with Qwen2.5‑0.5B

This article explains the GRPO reinforcement‑learning algorithm, shows its core idea of internal group competition without a separate evaluator model, and provides a complete, step‑by‑step code walkthrough—including environment setup, dataset preparation, reward‑function design, training configuration, and evaluation—using the Qwen2.5‑0.5B‑Instruct model on the GSM8K math dataset.

GRPOGSM8KQwen2.5

0 likes · 23 min read

Implement GRPO to Give LLMs Reasoning Ability with Qwen2.5‑0.5B