robert washbourne's picture

robert washbourne PRO

rawsh

·

rawsh

AI & ML interests

distributed systems, codegen

Recent Activity

new activity 8 days ago

PRIME-RL/Eurus-2-RL-Data:some empty code ground truths (roughly 1k in train)

liked a model 10 days ago

internlm/OREAL-7B

updated a dataset 11 days ago

rawsh/aime_2025

View all activity

Organizations

None yet

models 28

rawsh/q1-3B-PRIME

Text Generation • Updated Jan 20 • 113 • 1

rawsh/q1-3B-PRIME-PRM

Updated Jan 20 • 59

rawsh/SmallThinker-3B

Updated Jan 15 • 11

rawsh/Qwen2.5-0.5b-Eurus-2-PRIME

Updated Jan 15 • 13

rawsh/Qwen2.5-0.5b-Eurus-2-SFT

Text Generation • Updated Jan 13 • 51

rawsh/q1-Qwen2.5-0.5b

Text Generation • Updated Jan 7 • 49

rawsh/q1-Qwen2.5-0.5b-Instruct

Text Generation • Updated Jan 7 • 7

rawsh/MetaMath-Qwen2.5-0.5b

Text Generation • Updated Nov 25, 2024 • 80

rawsh/MetaMath-Qwen2.5-0.5b-PRM

Updated Nov 14, 2024 • 8

rawsh/mirrorqwen2.5-0.5b-prm

Text Classification • Updated Nov 12, 2024 • 20

datasets 18

rawsh/aime_2025

Viewer • Updated 11 days ago • 30 • 252

rawsh/Eurus-2-RL-Data-QwenSysPrompt

Viewer • Updated Jan 25 • 484k • 225

rawsh/Eurus-2-RL-Data-ProblemsOnly

Viewer • Updated Jan 15 • 484k • 206

rawsh/mirrorqwen2.5-0.5B-gsm8k-PRM-data-ORPO-2

Viewer • Updated Nov 12, 2024 • 20.2k • 27

rawsh/mirrorqwen2.5-0.5B-gsm8k-policy-data-ORPO-2

Viewer • Updated Nov 12, 2024 • 7.19k • 22

rawsh/mirrorqwen2.5-0.5B-gsm8k-policy-data-ORPO-1

Viewer • Updated Nov 12, 2024 • 7.38k • 19

rawsh/mirrorqwen2.5-0.5B-gsm8k-PRM-data-ORPO-1

Viewer • Updated Nov 12, 2024 • 21.6k • 24

rawsh/mirrorqwen2.5-0.5B-gsm8k-policy-data-ST-3

Viewer • Updated Nov 11, 2024 • 2.7k • 26

rawsh/mirrorqwen2.5-0.5B-gsm8k-PRM-data-ST-3

Viewer • Updated Nov 11, 2024 • 18k • 27

rawsh/mirrorqwen2.5-0.5B-gsm8k-policy-data-ST-2

Viewer • Updated Nov 11, 2024 • 2.65k • 15