Surrogate code verifiers across three model sizes trained using multiple different algorithms as described in the Aletheia paper
Aletheia
community
AI & ML interests
None defined yet.
models 21
Aletheia-Bench/DPO-Think-14B
Text Generation • 15B • Updated • 17 • 1
Aletheia-Bench/DPO-Think-1.5B
Text Generation • 2B • Updated • 31 •
Aletheia-Bench/BatchOnline-GRPO-7B
Text Generation • 8B • Updated • 25 • 1
Aletheia-Bench/BatchOnline-GRPO-14B
Text Generation • 15B • Updated • 14 • 1
Aletheia-Bench/BatchOnline-GRPO-1.5B
Text Generation • 2B • Updated • 12
Aletheia-Bench/GRPO-Think-14B-8k
Text Generation • 15B • Updated • 12 • 1
Aletheia-Bench/GRPO-Think-7B-8k
Text Generation • 8B • Updated • 25
Aletheia-Bench/GRPO-Think-14B-4k
Text Generation • 15B • Updated • 18
Aletheia-Bench/RAFT-7B
8B • Updated • 22
Aletheia-Bench/GRPO-Think-1.5B-8k
Text Generation • 2B • Updated • 10
datasets 9
Aletheia-Bench/Aletheia-Train-Questions
Viewer • Updated • 3.57k • 10
Aletheia-Bench/Aletheia-Mixed-DPO
Viewer • Updated • 50k • 14
Aletheia-Bench/Aletheia-Mixed
Viewer • Updated • 50k • 12
Aletheia-Bench/Aletheia-Heldout
Viewer • Updated • 33.3k • 19
Aletheia-Bench/Aletheia-Strong
Viewer • Updated • 57.3k • 76
Aletheia-Bench/Aletheia-Train
Viewer • Updated • 50k • 18
Aletheia-Bench/Aletheia-Adv
Viewer • Updated • 18k • 433
Aletheia-Bench/Aletheia-DPO
Viewer • Updated • 50k • 34
Aletheia-Bench/Aletheia-Hard
Viewer • Updated • 18k • 23