COMMITS
May 14, 2025
S
fix: add default arg for push_to_hub (#240)
Stephan Tulkens committed
May 8, 2025
T
Fix dates in README.md (#238)
Thomas van Dongen committed
May 3, 2025
I
docs: update chonkie link on tutorial readme (#235)
Italo A. committed
April 30, 2025
S
increment version (#232)
Stephan Tulkens committed
S
docs: add info about quantization and dimensionality reduction (#231)
Stephan Tulkens committed
April 28, 2025
S
fix issue with unk in unigram (#227)
Stephan Tulkens committed
S
fix: precision during training (#228)
Stephan Tulkens committed
S
fix 0 score in evaluate (#226)
Stephan Tulkens committed
April 27, 2025
S
fix: issues with unk and pad (#225)
Stephan Tulkens committed
April 25, 2025
S
fix: typing issues, bug in infernece (#224)
Stephan Tulkens committed
S
feat: track token provenance (#222)
Stephan Tulkens committed
April 24, 2025
S
feat: faster inference for large vocab (#221)
Stephan Tulkens committed
T
feat: Added quantization for from_sentence_transformers (#219)
Thomas van Dongen committed
April 22, 2025
S
feat: add subfolder loading (#218)
Stephan Tulkens committed
April 21, 2025
S
feat: add quantization (#217)
Stephan Tulkens committed
S
feat: add dimensionality during loading (#216)
Stephan Tulkens committed
S
fix: pretokenize tokens before checking vocabulary (#215)
Stephan Tulkens committed
T
feat: Added py typed file (#214)
Thomas van Dongen committed
April 10, 2025
S
fix bibtex (#208)
Stephan Tulkens committed
April 9, 2025
S
rewrite backend (#207)
Stephan Tulkens committed
March 2, 2025
B
fix: Updated semantic chunking tutorial
Bhavnick Minhas committed
February 28, 2025
T
Bump version (#204)
Thomas van Dongen committed
February 26, 2025
S
fix: only allows named args in pretrain (#200)
Stephan Tulkens committed
T
docs: Added discord badge (#193)
Thomas van Dongen committed
February 17, 2025
T
feat: Add evaluate function for classifiers (#195)
Thomas van Dongen committed
February 16, 2025
T
feat: Add multilabel classification for training (#191)
Thomas van Dongen committed
February 15, 2025
T
docs: Update model card template (#192)
Thomas van Dongen committed
February 14, 2025
T
feat: Added min and max epochs to fit (#190)
Thomas van Dongen committed
T
docs: Added training plot, added more training results (#189)
Thomas van Dongen committed
February 12, 2025
T
Bump version (#188)
Thomas van Dongen committed