ML-Intern-lab
/

nanochat

Model card Files Files and versions

264 kB

Ctrl+K

Ctrl+K

67 contributors

History: 81 commits

Andrej Karpathy

delete datasets dependency bye

a5a3a33 4 months ago

LEADERBOARD.md

13 kB
nuke huggingface and its giant dependency footprint from orbit. datasets still todo 4 months ago
LOG.md

63.4 kB
tried and failed at DyT 6 months ago
estimate_gpt3_core.ipynb

73.1 kB
add notebook on deriving the CORE estimates for the GPT-3 miniseries. 10 months ago
nanochat.png

1.31 kB
Update logo about 1 year ago
repackage_data_reference.py

4.58 kB
delete datasets dependency bye 4 months ago
scaling_analysis.ipynb

15.2 kB
fix scaling laws scripts after the bigram embeddings were removed 8 months ago
scaling_laws_jan26.png

93.1 kB
nuke midtraining from orbit, it's not as needed now that we have a BOS-aligned dataloader. Also change the README a lot. midtrianing is not yet fully properly erased across the board, but good enough for step 1 9 months ago