rlundqvist/ifeval-obf-noleak-r63
Reinforcement Learning • Updated • 18
Ryan Lundqvist
rlundqvist
·
AI & ML interests
None yet
Recent Activity
published a model 17 days ago
rlundqvist/ifeval-obf-noleak-r63 updated a model 17 days ago
rlundqvist/ifeval-obf-noleak-r63 updated a dataset 18 days ago
rlundqvist/ifeval-obf-rl-run-leakOrganizations
models 8
rlundqvist/wood-ifeval-obfuscated-r180
Updated • 12
rlundqvist/rm-2023-leak-full
Updated • 15
rlundqvist/rm-2023-noleak-full
Updated • 18
rlundqvist/rm-2023-noleak-6k
Updated • 21
rlundqvist/ifeval-obf-rl-run
Updated
rlundqvist/ifeval-obf-rm-2026safe-qwen2.5-7b
Updated • 14
rlundqvist/ifeval-obf-rm-2023-qwen2.5-7b
Updated • 15
datasets 30
rlundqvist/ifeval-obf-rl-run-leak
Viewer • Updated • 180 • 348
rlundqvist/ifeval-obf-rl-preferences
Viewer • Updated • 16.4k • 77
rlundqvist/ifeval-obf-rl-run
Viewer • Updated • 36 • 93
rlundqvist/vea-rm-stress-tests
Updated • 73
rlundqvist/vea-generalization-benchmark
Viewer • Updated • 112 • 46
rlundqvist/exp14-rl-runs
Preview • Updated • 122
rlundqvist/exp10-constrained-choice-steering
Updated • 126
rlundqvist/exp5-ea-framing-dataset
Updated • 5
rlundqvist/exp2-cot-scaled-up
Updated • 8
rlundqvist/exp1-cot-eval-awareness
Preview • Updated • 25