arxiv:2605.05365
robert washbourne PRO
rawsh
AI & ML interests
distributed systems, codegen
Recent Activity
liked a dataset 25 days ago
OpenDataArena/Spark-234K liked a dataset about 1 month ago
TIGER-Lab/WebInstruct-CFT liked a model 3 months ago
Nanbeige/Nanbeige4.2-3BOrganizations
models 28
rawsh/MetaMath-Qwen2.5-0.5b-PRM
0.5B • Updated • 16
rawsh/q1-3B-PRIME
Text Generation • 3B • Updated • 31 • 2
rawsh/q1-3B-PRIME-PRM
3B • Updated • 15
rawsh/SmallThinker-3B
3B • Updated • 11
rawsh/Qwen2.5-0.5b-Eurus-2-PRIME
0.6B • Updated • 12
rawsh/Qwen2.5-0.5b-Eurus-2-SFT
Text Generation • 0.6B • Updated • 25
rawsh/q1-Qwen2.5-0.5b
Text Generation • 0.6B • Updated • 21
rawsh/q1-Qwen2.5-0.5b-Instruct
Text Generation • 0.6B • Updated • 14
rawsh/MetaMath-Qwen2.5-0.5b
Text Generation • 0.6B • Updated • 37
rawsh/mirrorqwen2.5-0.5b-prm
Text Classification • 0.5B • Updated • 17
datasets 22
rawsh/codeforces-correct-incorrect
Viewer • Updated • 7.14k • 12
rawsh/bigdeepmath
Updated • 3
rawsh/2024_AMC12
Viewer • Updated • 45 • 361
rawsh/amc23
Viewer • Updated • 83 • 36
rawsh/aime_2025
Viewer • Updated • 30 • 58
rawsh/Eurus-2-RL-Data-QwenSysPrompt
Viewer • Updated • 484k • 48
rawsh/Eurus-2-RL-Data-ProblemsOnly
Viewer • Updated • 484k • 75
rawsh/mirrorqwen2.5-0.5B-gsm8k-PRM-data-ORPO-2
Viewer • Updated • 20.2k • 7
rawsh/mirrorqwen2.5-0.5B-gsm8k-policy-data-ORPO-2
Viewer • Updated • 7.19k • 15
rawsh/mirrorqwen2.5-0.5B-gsm8k-policy-data-ORPO-1
Viewer • Updated • 7.38k • 14