-
Update README.md
-
Update README.md
-
Update README.md
-
Update README.md
-
fix: add missing `errors`
-
feat: add pickle support
-
fix: make `eos_token`/`pad_token` overridable
-
feat: expose tiktoken tokenizer merge ranks and special tokens
-
fix: check surface form against special tokens in `_add_tokens`
-
fix: update license
-
fix: store `cl100k_base` mergeable ranks in `arcade100k.tiktoken`
-
Merge branch 'main' of hf.co:jon-tow/stablelm-tokenizer-v1 into main
-
fix: re-ordering special tokens
-
Create tokenizer_config.json
-
Delete tokenizer_config.json
-
Delete special_tokens_map.json
-
fix: pass in `vocab_file` to tiktoken loader
-
Upload tokenizer
-
fix: remove `print` debug statements
-
Update tokenization_arcade100k.py
-
Update README.md
-
fix: create final list of special tokens
-
init: first commit
-
initial commit