RabotniKuma/Fast-Math-R1-GRPO download history
RabotniKuma/Fast-Math-R1-GRPO is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 76 times (29 in the last 7 days), and 1,719 times in total. It ranks #186,937 among datasets by monthly downloads.
This repository contains the second-stage GRPO dataset for the paper A Practical Two-Stage Recipe for Mathematical LLMs: Maximizing Accuracy with SFT and Efficiency with Reinforcement Learning. This dataset is crucial for the second stage of the training recipe, aiming to improve token efficiency wh
Models trained on Fast-Math-R1-GRPO
2 models list it as training data.
- mradermacher/Fast-Math-R1-14B-GGUF 598 downloads in 30 days
- RabotniKuma/Fast-Math-R1-14B 34 downloads in 30 days
Open RabotniKuma/Fast-Math-R1-GRPO on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.