ThomasTheMaker/pico-decoder-tiny-experiments
Updated
Pico LM
Pre-training 11M parameter models on 29k, 5M, 10M, 20M, & 205M rows of Dolma dataset using pico-lm
-
-
ThomasTheMaker/tiny-Dolma205M
11.3M • Updated • 3 -
ThomasTheMaker/pico-decoder-tiny-dolma10M-v1
Updated -
ThomasTheMaker/tiny-dolma20M
11.3M • Updated • 6 -
ThomasTheMaker/tiny-dolma10M
11.3M • Updated • 2 -
ThomasTheMaker/pico-decoder-tiny
11.3M • Updated • 10 -
ThomasTheMaker/pretokenized_wiki_en
Viewer • Updated • 448k • 880 -
ThomasTheMaker/pretokenized-dolma-100M
Updated • 9 -
ThomasTheMaker/pretokenized-dolma-10M
Viewer • Updated • 11.3M • 1.05k -
ThomasTheMaker/pretokenized-dolma-20M
Viewer • Updated • 22.6M • 983 -
ThomasTheMaker/pretokenized-dolma-5M
Viewer • Updated • 5.65M • 547 -
ThomasTheMaker/fineweb-edu-6parquet-processed
Updated • 28