BabyLM Sequence Length

community

AI & ML interests

BabyLM 2025 paper submission

babylm-seqlen 's models 50

babylm-seqlen/opt-256

0.1B • Updated Jun 3 • 9

babylm-seqlen/opt-512

0.1B • Updated Jun 3 • 7

babylm-seqlen/opt-1024

0.1B • Updated Jun 3 • 7

babylm-seqlen/mamba-1024

0.2B • Updated Jun 3 • 6

babylm-seqlen/mamba-512

0.2B • Updated Jun 3 • 5

babylm-seqlen/mamba-256

0.2B • Updated Jun 3 • 6

babylm-seqlen/mamba-128

0.2B • Updated Jun 3 • 8

babylm-seqlen/mamba-64

0.2B • Updated Jun 3 • 8

babylm-seqlen/opt-128

0.1B • Updated Jun 3 • 6

babylm-seqlen/opt-64

0.1B • Updated Jun 3 • 11

babylm-seqlen/opt-256-warmup

0.1B • Updated May 31 • 7

babylm-seqlen/opt-128-warmup

0.1B • Updated May 31 • 7

babylm-seqlen/opt-64-warmup

0.1B • Updated May 31 • 7

babylm-seqlen/opt-512-warmup

0.1B • Updated May 31 • 7

babylm-seqlen/opt-2048-warmup

0.1B • Updated May 31 • 4

babylm-seqlen/opt-4096-warmup

0.1B • Updated May 31 • 5

babylm-seqlen/opt-8192-warmup

0.1B • Updated May 31 • 8

babylm-seqlen/opt-1024-warmup

0.1B • Updated May 31 • 6

babylm-seqlen/opt-dummy

0.1B • Updated Apr 21 • 5

babylm-seqlen/tokenizer