osmarks/nanogpt-experiments

mirror of https://github.com/osmarks/nanogpt-experiments.git synced 2025-02-07 14:40:03 +00:00

History

Christian Orr 36c7db8c44

bugfix in decode function

Return was left out of the decoder, so it didn't work.

2023-03-08 10:16:19 +02:00

..

prepare.py

bugfix in decode function

2023-03-08 10:16:19 +02:00

readme.md

add support for character-level language models, a new character-level shakespeare dataset, a new config file that shows how to train a character-level baby GPT on it, and adjust the sample function to figure out if it should decode with characters or GPT2 bpe tokens. The current implementation is a bit hacky and basically assumes just these two possibilities. In the future we may want to support more general encoders or decoders.

2023-01-11 05:27:19 +00:00

readme.md

tiny shakespeare, character-level

Tiny shakespeare, of the good old char-rnn fame :) Treated on character-level.

After running prepare.py:

train.bin has 1,003,854 tokens
val.bin has 111,540 tokens