Checkpoints (bf16, 50-step) + train/eval data for RLTR (transfer-reward RL) incl. cross-family (gemma) receiver.
HyunseokLee
hyunseoki
AI & ML interests
None yet
Recent Activity
updated a collection 31 minutes ago
RLTR: Learning Robust Reasoning via Transfer updated a dataset 32 minutes ago
hyunseoki/rltr-data published a dataset 33 minutes ago
hyunseoki/rltr-dataOrganizations
models 77
hyunseoki/rltr-qwen3-8b-to-gemma4b-polaris
Updated
hyunseoki/rltr-qwen3-4b-polaris-baseline
Updated
hyunseoki/rltr-qwen3-4b-to-1p7b-polaris
Updated
hyunseoki/rltr-qwen3-8b-to-4b-polaris
Updated
hyunseoki/rltr-qwen3-8b-to-4b-deepmath
Updated
hyunseoki/rltr-qwen3-8b-polaris-baseline
Updated
hyunseoki/mh-v1b-math-4b-sym-sp2
Text Generation • 4B • Updated
hyunseoki/mh-v1b-imo-9b-taonly-baseline
Text Generation • 9B • Updated
hyunseoki/mh-v1b-imo-9b-reclaim-neg
Text Generation • 9B • Updated
hyunseoki/mh-v1b-pr-9b-reclaim-neg
Text Generation • 9B • Updated
datasets 18
hyunseoki/rltr-data
Updated
hyunseoki/mh-v1b-scaffolds
Updated
hyunseoki/regUIDE-rebuttal-artifacts
Updated • 123
hyunseoki/memory-reasoning-split-eval-sets
Preview • Updated • 109
hyunseoki/popqa-mini-ner-knowledge-masks
Preview • Updated • 11
hyunseoki/qwen3-0p6b-openthoughts-self-distill-10k
Preview • Updated • 7
hyunseoki/qwen3-0p6b-openthoughts-self-distill-1k
Preview • Updated • 11
hyunseoki/openthoughts3-dedup-index
Updated • 9
hyunseoki/numina-math-10k-seed13
Viewer • Updated • 11k • 12
hyunseoki/prefixgen_MATH
Viewer • Updated • 60k • 34