RabotniKuma/Fast-Math-R1-SFT download history

RabotniKuma/Fast-Math-R1-SFT is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 170 times (51 in the last 7 days), and 2,922 times in total. It ranks #101,111 among datasets by monthly downloads.

This repository contains the First stage SFT dataset as presented in the paper A Practical Two-Stage Recipe for Mathematical LLMs: Maximizing Accuracy with SFT and Efficiency with Reinforcement Learning. This dataset is used for the intensive Supervised Fine-Tuning (SFT) phase, crucial for pushing t

Models trained on Fast-Math-R1-SFT

3 models list it as training data.

Open RabotniKuma/Fast-Math-R1-SFT on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.