Hana-ame
/

additive-rand-transformer

Reinforcement Learning

chain-of-thought

Model card Files Files and versions

additive-rand-transformer / checkpoints

36 MB

Ctrl+K

Ctrl+K

1 contributor

History: 10 commits

Hana-ame's picture

feat: publish seg2_b16 checkpoint (L4·D64 seg2 b16, bottleneck seg variant) via git-lfs

0873db2 2 days ago

l2_d64_attn_causal.pt

677 kB
xet

feat: package layout + model card + 7 checkpoints 3 days ago
l2_d64_attn_dsa.pt

677 kB
xet

feat: package layout + model card + 7 checkpoints 3 days ago
l4_d128_cot_bias05_final.pt

11.2 MB
xet

feat: package layout + model card + 7 checkpoints 3 days ago
l4_d128_grpo_final.pt

3.73 MB
xet

feat: package layout + model card + 7 checkpoints 3 days ago
l4_d128_reinforce_conservative.pt

3.73 MB
xet

feat: package layout + model card + 7 checkpoints 3 days ago
l4_d128_selfplay_anchor.pt

3.73 MB
xet

feat: package layout + model card + 7 checkpoints 3 days ago
l4_d128_sft_nobias_final.pt

11.2 MB
xet

feat: package layout + model card + 7 checkpoints 3 days ago
l4_d64_seg2_b16.pt

1.1 MB
xet

feat: publish seg2_b16 checkpoint (L4·D64 seg2 b16, bottleneck seg variant) via git-lfs 2 days ago