BabyLM Sequence Length

babylm-seqlen 's models 50

Sort:  Recently updated

babylm-seqlen/opt-2048-warmup-v2

0.1B • Updated Jun 30 • 40

babylm-seqlen/mamba-2048-warmup-v2

0.2B • Updated Jun 30 • 38

babylm-seqlen/mamba-64-warmup-v2

0.2B • Updated Jun 26 • 40

babylm-seqlen/mamba-8192-warmup-v2

0.2B • Updated Jun 26 • 28

babylm-seqlen/mamba-4096-warmup-v2

0.2B • Updated Jun 26 • 41

babylm-seqlen/opt-8192-warmup-v2

0.1B • Updated Jun 25 • 48

babylm-seqlen/opt-4096-warmup-v2

0.1B • Updated Jun 25 • 39

babylm-seqlen/mamba-128-warmup-v2

0.2B • Updated Jun 25 • 20

babylm-seqlen/mamba-512-warmup-v2

0.2B • Updated Jun 25 • 47

babylm-seqlen/mamba-1024-warmup-v2

0.2B • Updated Jun 25 • 66

babylm-seqlen/opt-128-warmup-v2

0.1B • Updated Jun 24 • 35

babylm-seqlen/opt-256-warmup-v2

0.1B • Updated Jun 24 • 47

babylm-seqlen/opt-512-warmup-v2

0.1B • Updated Jun 24 • 48

babylm-seqlen/mamba-256-warmup-v2

0.2B • Updated Jun 15 • 48

babylm-seqlen/opt-1024-warmup-v2

0.1B • Updated Jun 15 • 7

babylm-seqlen/opt-64-warmup-v2

0.1B • Updated Jun 14 • 42

babylm-seqlen/mamba-4096

0.2B • Updated Jun 6 • 24

babylm-seqlen/opt-8192

0.1B • Updated Jun 6 • 21

babylm-seqlen/opt-4096

0.1B • Updated Jun 6 • 22

babylm-seqlen/mamba-8192

0.2B • Updated Jun 3 • 21

babylm-seqlen/mamba-8192-warmup

0.2B • Updated Jun 3 • 22

babylm-seqlen/mamba-4096-warmup

0.2B • Updated Jun 3 • 22

babylm-seqlen/mamba-2048-warmup

0.2B • Updated Jun 3 • 9

babylm-seqlen/mamba-512-warmup

0.2B • Updated Jun 3 • 10

babylm-seqlen/mamba-1024-warmup

0.2B • Updated Jun 3 • 7

babylm-seqlen/mamba-64-warmup

0.2B • Updated Jun 3 • 8

babylm-seqlen/mamba-128-warmup

0.2B • Updated Jun 3 • 7

babylm-seqlen/mamba-256-warmup

0.2B • Updated Jun 3 • 10

babylm-seqlen/opt-2048

0.1B • Updated Jun 3 • 24

babylm-seqlen/mamba-2048

0.2B • Updated Jun 3 • 8