Releases: urchade/GLiNER
Releases · urchade/GLiNER
v0.2.22
What's Changed
- jieba3 added by @oleksandrlukashov in #269
- Update requirements.txt to not use onnxruntime-gpu for mac by @anny-lanai in #271
- Add StanzaWordsSplitter for language-aware tokenization by @anthonyyazdani in #276
- Implement Assymetric loss by @Ingvarstep in #272
- Fixed ALL_LAYERNORM_LAYERS bug by @dcrey7 in #278
- Add generation with constraints by @Ingvarstep in #283
- loss reduction argument fixed by @BioMikeUkr in #286
- Labels decoder by @Ingvarstep in #282
- Fix Cython modules usage by @Ingvarstep in #287
- Converts
textsgiven as a single str to list by @jackboyla in #288 - fix SpanBiEncoderProcessor label assignment by @cceyda in #289
New Contributors
- @anny-lanai made their first contribution in #271
- @anthonyyazdani made their first contribution in #276
- @dcrey7 made their first contribution in #278
- @BioMikeUkr made their first contribution in #286
- @jackboyla made their first contribution in #288
- @cceyda made their first contribution in #289
Full Changelog: 0.2.21...v0.2.22
0.2.21
What's Changed
- Add return index for relation extraction by @rafmacalaba in #260
- Multilang splitter by @oleksandrlukashov in #265
- Fix multi-gpu training for both span and token-level models by @Ingvarstep in #266
New Contributors
- @oleksandrlukashov made their first contribution in #265
Full Changelog: v0.2.20...0.2.21
v0.2.20
What's Changed
- Update relation_extraction.py by @rafmacalaba in #255
- add cache_dir parameter to AutoConfig, AutoTokenizer by @bit2244 in #250
- add load from config by @urchade in #257
- Add support of Flash DeBERTa by @Ingvarstep in #259
New Contributors
- @rafmacalaba made their first contribution in #255
- @bit2244 made their first contribution in #250
Full Changelog: v0.2.19...v0.2.20
v0.2.19
v0.2.17
What's Changed
- Fix bug in text classification evaluation by @seanbenhur in #228
New Contributors
- @seanbenhur made their first contribution in #228
Full Changelog: v0.2.16...v0.2.17
v0.2.16
**best support of multi-label for span-based ner training
Full Changelog: v0.2.15...v0.2.16
v0.2.15
What's Changed
- make
onnxruntime-gpuoptional by @moritzwilksch in #223
Full Changelog: v0.2.14...v0.2.15
v0.2.14
What's Changed
- Bug fix: Tensors should not be moved to a device when using onnx by @azikoss in #196
- Bug fix: Tensors should not be moved to a device when using onnx (in evaluate function) by @wojiaodawei in #199
- Change how the config file is loaded by @eriknovak in #206
- Add GPU Support for ONNX Models by @KarimLulu in #201
- Simplify inference and evaluation for multi-task models by @Ingvarstep in #217
New Contributors
- @azikoss made their first contribution in #196
- @wojiaodawei made their first contribution in #199
- @eriknovak made their first contribution in #206
- @KarimLulu made their first contribution in #201
Full Changelog: v0.2.13...v0.2.14
v0.2.13
Full Changelog: v0.2.12...v0.2.13