SentencePiece tokenizer and encoded corpus retained for reproducibility.
Miguel Cárdenas
miguelcsx
AI & ML interests
None yet
Organizations
None yet
models 73
miguelcsx/mosaic-sleep-d384-bbpe16k
Fill-Mask • 33.3M • Updated • 20
miguelcsx/mosaic-joint-d384-bbpe16k
Fill-Mask • 33.3M • Updated • 14
miguelcsx/mosaic-memory-d384-bbpe16k
Fill-Mask • 33.3M • Updated • 20
miguelcsx/mosaic-views-d384-bbpe16k
Fill-Mask • 33.3M • Updated • 15
miguelcsx/dial-shuffled-s2
39.6M • Updated • 5
miguelcsx/dial-shuffled-s1
39.6M • Updated • 5
miguelcsx/dial-shuffled-s5
39.6M • Updated • 5
miguelcsx/dial-shuffled-s4
39.6M • Updated • 3
miguelcsx/dial-shared-s1
39.6M • Updated • 8
miguelcsx/dial-aligned-s0
39.6M • Updated • 3
datasets 25
miguelcsx/dial-workshop-data
Updated • 37
miguelcsx/dial-lexical-scaffold-priors
Updated • 7
miguelcsx/factorized-resource-paper-data
Updated • 145
miguelcsx/factorized-mechanism-paper-data
Updated • 95
miguelcsx/babylm-2026-tournament-evidence
Preview • Updated • 22
miguelcsx/factorized-strict-small-null-corpus
Updated • 35
miguelcsx/factorized-strict-small-real-corpus
Updated • 23
miguelcsx/factorized-strict-small-natural-corpus
Updated • 22
miguelcsx/factorized-strict-small-priors
Updated • 44
miguelcsx/prism-boundary-bpe16k-corpus
Updated • 65