sparklereasoning

non-profit

https://sparkle-reasoning.github.io/

sparkle-reasoning

AI & ML interests

None defined yet.

Recent Activity

MilaWang updated a model 10 days ago

sparkle-reasoning/SparkleRL-7B-Stage1

MilaWang updated a model 10 days ago

sparkle-reasoning/SparkleRL-7B-Stage2-aug

MilaWang authored a paper about 1 month ago

Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learning

View all activity

models 4

sparkle-reasoning/SparkleRL-7B-Stage1

Reinforcement Learning • 8B • Updated 10 days ago • 14 • 2

sparkle-reasoning/SparkleRL-7B-Stage2-aug

Reinforcement Learning • 8B • Updated 10 days ago • 11 • 3

sparkle-reasoning/SparkleRL-7B-Stage2-mix

Text Generation • 8B • Updated May 15 • 2

sparkle-reasoning/SparkleRL-7B-Stage2-hard

Text Generation • 8B • Updated May 15

datasets 7

sparkle-reasoning/olympiad_bench

Viewer • Updated Jul 4 • 675 • 16

sparkle-reasoning/math500

Viewer • Updated Jul 4 • 500 • 12

sparkle-reasoning/gsm8k

Viewer • Updated Jul 4 • 1.32k • 7

sparkle-reasoning/hardmath

Viewer • Updated Jun 13 • 6.5k • 269

sparkle-reasoning/dsr40k

Viewer • Updated Jun 13 • 40.3k • 16

sparkle-reasoning/aime2024

Viewer • Updated Jun 13 • 30 • 23

sparkle-reasoning/amc2023

Viewer • Updated May 6 • 40 • 46