issues
search
delphi-suite
/
delphi
small language models training made easy
Apache License 2.0
8
stars
1
forks
source link
tokenizer & tokenization improvements
#136
Closed
jettjaniak
closed
1 month ago
jettjaniak
commented
1 month ago
see commit messages
TODO
[ ] retrain and upload the tokenizer
[ ] retokenize and upload the tokenized stories dataset
[ ] fix tests
see commit messages
TODO