Keras-nlp

KerasNLP is adding experimental support for Jax and PyTorch backends on top of the **Keras Core** library. Read the [anouncement](https://keras.io/keras_core/announcement/), and browse the [full library documentation](http://keras.io/keras_core/), including how to specify the backend when running your code.

Support for both Jax and PyTorch is still experimental, expect some rough edges and please give us feedback!

Summary
* This release should be equivalent to `0.5.2` with the addition of multi-backend support.
* The following API symbols are currently restricted to the tensorflow backend:
* `keras_nlp.models.DebertaV3*`
* `keras_nlp.models.FNet*`
* `keras_nlp.metrics`
* `keras_nlp.samplers.BeamSampler`
* `keras_nlp.samplers.ContrastiveSampler`
* Note that there are two ways you can run on top of Tensorflow.
* If you run your scripts/colab without any changes, KerasNLP will use **tf.keras** for all layer and modeling implementations. This should be a no-op from previous releases of the library.
* If you run your scripts/colab with `KERAS_BACKEND={jax, torch, tensorflow}`, you will be trying the new **Keras Core** library, using the specified backend. This is a great way to test out the future of the library!
* Full details on runtime specification is available along with the [Keras Core documentation](http://keras.io/keras_core/).

What's Changed
* small updates to the release doc by chenmoneygithub in https://github.com/keras-team/keras-nlp/pull/1031
* Sampler docstring edit by abuelnasr0 in https://github.com/keras-team/keras-nlp/pull/1033
* Fix program crash for id_to_token() method in SentencePieceTokenizer by abuelnasr0 in https://github.com/keras-team/keras-nlp/pull/1040
* Update our release process to preview docs before release by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1043
* Add Whisper Tokenizer and Audio Feature Extractor by abheesht17 in https://github.com/keras-team/keras-nlp/pull/847
* Also strip padding token for opt by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1028
* Add regex dep by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1044
* Add BartSeq2SeqLM and conditional text generation with BART by abheesht17 in https://github.com/keras-team/keras-nlp/pull/974
* Support list/tuple inputs for special tokens in StartEndPacker layer by abheesht17 in https://github.com/keras-team/keras-nlp/pull/1045
* Support list/tuple inputs for special tokens in MultiSegmentPacker layer by abheesht17 in https://github.com/keras-team/keras-nlp/pull/1046
* Fix a misleading part of our cached MHA docs by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1048
* Always pass weight name by kwarg by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1053
* Always pass metrics in a list or dict by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1054
* Move `Defaults to` to end of arg docstring and standardise values by SamuelMarks in https://github.com/keras-team/keras-nlp/pull/1057
* Fix beam search for BART by abheesht17 in https://github.com/keras-team/keras-nlp/pull/1058
* Replace tf.dtype with "dtype" by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1059
* Test shapes directly by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1064
* Clean up metrics tests by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1063
* Remove metrics merge tests by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1065
* Fix whisper feature inputs by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1069
* Always specify shape when creating variables by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1067
* Remove ragged support from position embeddings by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1068
* Clean up dtype handling for preprocessing layers by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1066
* Add BART finetuned on CNN+DM for summarisation by abheesht17 in https://github.com/keras-team/keras-nlp/pull/1060
* Fix saving bug by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1073
* Fix t5 forward pass by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1082
* Feat/make transformer decoder callable without causal mask by ferraric in https://github.com/keras-team/keras-nlp/pull/1083
* Adding `GPTNeoXBackbone` by shivance in https://github.com/keras-team/keras-nlp/pull/1056
* Add a common test case by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1095
* Update register_keras_serializable to use saving module by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1094
* Don't test tf format by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1104
* Add `GPTNeoXPreprocessor` by shivance in https://github.com/keras-team/keras-nlp/pull/1093
* Split layers into layers/modeling & layers/preprocessing by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1102
* Fix merge conflict from 1102 by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1105
* Add a common base class for generative models by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1096
* Add `GPTNeoXCausalLMPreprocessor` by shivance in https://github.com/keras-team/keras-nlp/pull/1106
* Add Whisper Presets by abheesht17 in https://github.com/keras-team/keras-nlp/pull/1089
* Refactor `RotaryEmbedding` and `GPTNeoXAttention` by shivance in https://github.com/keras-team/keras-nlp/pull/1101
* Remove all the secret keys for ci by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1126
* Fix publish to pypi action by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1127
* Unexport models that are not in the 0.6 release by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1125
* Bump the version to 0.6.0 by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1128

New Contributors
* SamuelMarks made their first contribution in https://github.com/keras-team/keras-nlp/pull/1057
* ferraric made their first contribution in https://github.com/keras-team/keras-nlp/pull/1083

**Full Changelog**: https://github.com/keras-team/keras-nlp/compare/v0.5.2...v0.6.0

What's Changed
* Fix unclosed fenced docstrings by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1025
* Fix a bug with computing the output mask after generate by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1029


**Full Changelog**: https://github.com/keras-team/keras-nlp/compare/v0.5.1...v0.5.2

What's Changed
* Fix typos in export by chenmoneygithub in https://github.com/keras-team/keras-nlp/pull/1024


**Full Changelog**: https://github.com/keras-team/keras-nlp/compare/v0.5.0...v0.5.1

In this 0.5 release, we are bringing generative AI to KerasNLP!

Summary
* Added text generation task model `keras_nlp.models.GPT2CausalLM` and `keras_nlp.models.OPTCausalLM` along with corresponding preprocessors. Both task models exposed a public `generate()` method for text generation.
* Refactored text generation utils into sampler APIs in `keras_nlp.samplers` for better UX and scalability.
* Added MaskedLM task models `keras_nlp.models.XXXMaskedLM`, e.g., `keras_nlp.models.BertMaskedLM`.

What's Changed
* Update python version in readme to 3.8 by haifeng-jin in https://github.com/keras-team/keras-nlp/pull/618
* Modify our pip install line so we upgrade tf by mattdangerw in https://github.com/keras-team/keras-nlp/pull/616
* Use Adam optimizer for quick start by mattdangerw in https://github.com/keras-team/keras-nlp/pull/620
* Clean up class name and `self` in calls to `super()` by mbrukman in https://github.com/keras-team/keras-nlp/pull/628
* Update word_piece_tokenizer.py by ADITYADAS1999 in https://github.com/keras-team/keras-nlp/pull/617
* Add DeBERTaV3 Conversion Script by abheesht17 in https://github.com/keras-team/keras-nlp/pull/633
* Add AlbertTokenizer and AlbertPreprocessor by abheesht17 in https://github.com/keras-team/keras-nlp/pull/627
* Create `Backbone` base class by jbischof in https://github.com/keras-team/keras-nlp/pull/621
* Add TPU testing by chenmoneygithub in https://github.com/keras-team/keras-nlp/pull/591
* Add Base Preprocessor Class by abheesht17 in https://github.com/keras-team/keras-nlp/pull/638
* Add keras_nlp.samplers by chenmoneygithub in https://github.com/keras-team/keras-nlp/pull/563
* Add ALBERT Backbone by abheesht17 in https://github.com/keras-team/keras-nlp/pull/622
* Add a small script to count parameters in our presets by mattdangerw in https://github.com/keras-team/keras-nlp/pull/610
* Clean up examples/ directory by ADITYADAS1999 in https://github.com/keras-team/keras-nlp/pull/637
* Fix Small BERT Typo by abheesht17 in https://github.com/keras-team/keras-nlp/pull/651
* Rename examples/bert -> examples/bert_pretraining by mattdangerw in https://github.com/keras-team/keras-nlp/pull/647
* Add FNet Preprocessor by abheesht17 in https://github.com/keras-team/keras-nlp/pull/646
* Add FNet Backbone by abheesht17 in https://github.com/keras-team/keras-nlp/pull/643
* Small DeBERTa Docstring Fixes by abheesht17 in https://github.com/keras-team/keras-nlp/pull/666
* Add Fenced Docstring Testing by abheesht17 in https://github.com/keras-team/keras-nlp/pull/640
* Corrected the epsilon value by soma2000-lang in https://github.com/keras-team/keras-nlp/pull/665
* Consolidate docstring formatting weirdness in Backbone and Preprocessor base classes by mattdangerw in https://github.com/keras-team/keras-nlp/pull/654
* Fix `value_dim` in `TransformerDecoder`'s cross-attn layer by abheesht17 in https://github.com/keras-team/keras-nlp/pull/667
* Add ALBERT Presets by abheesht17 in https://github.com/keras-team/keras-nlp/pull/655
* Add Base Task Class by abheesht17 in https://github.com/keras-team/keras-nlp/pull/671
* Implement TopP, TopK and Beam samplers by chenmoneygithub in https://github.com/keras-team/keras-nlp/pull/652
* Add FNet Presets by abheesht17 in https://github.com/keras-team/keras-nlp/pull/659
* Bump the year to 2023 by mattdangerw in https://github.com/keras-team/keras-nlp/pull/679
* Add BART Backbone by abheesht17 in https://github.com/keras-team/keras-nlp/pull/661
* Handle trainable and name in the backbone base class by mattdangerw in https://github.com/keras-team/keras-nlp/pull/680
* Ignore Task Docstring for Testing by abheesht17 in https://github.com/keras-team/keras-nlp/pull/683
* Light-weight benchmarking script by NusretOzates in https://github.com/keras-team/keras-nlp/pull/664
* Conditionally import tf_text everywhere by mattdangerw in https://github.com/keras-team/keras-nlp/pull/684
* Expose `token_embedding` as a Backbone Property by abheesht17 in https://github.com/keras-team/keras-nlp/pull/676
* Move `from_preset` to base tokenizer classes by shivance in https://github.com/keras-team/keras-nlp/pull/673
* add f_net_classifier and f_net_classifier_test by ADITYADAS1999 in https://github.com/keras-team/keras-nlp/pull/670
* import rouge_scorer directly from rouge_score package by sampathweb in https://github.com/keras-team/keras-nlp/pull/691
* Fix typo in requirements file juypter -> jupyter by mattdangerw in https://github.com/keras-team/keras-nlp/pull/693
* Temporary fix to get nightly green again by mattdangerw in https://github.com/keras-team/keras-nlp/pull/696
* GPT2 Text Generation APIs by chenmoneygithub in https://github.com/keras-team/keras-nlp/pull/592
* Run keras saving tests on nightly and fix RobertaClassifier test by mattdangerw in https://github.com/keras-team/keras-nlp/pull/692
* Speed up pip install keras-nlp; simplify deps by mattdangerw in https://github.com/keras-team/keras-nlp/pull/697
* Add `AlbertClassifier` by shivance in https://github.com/keras-team/keras-nlp/pull/668
* Make tokenizer, backbone, preprocessor properties settable on base class by mattdangerw in https://github.com/keras-team/keras-nlp/pull/700
* Update to latest black by mattdangerw in https://github.com/keras-team/keras-nlp/pull/708
* RobertaMaskedLM task and preprocessor by mattdangerw in https://github.com/keras-team/keras-nlp/pull/653
* Default compilation for BERT/RoBERTa classifiers by jbischof in https://github.com/keras-team/keras-nlp/pull/695
* Add start/end token padding to `GPT2Preprocessor` by chenmoneygithub in https://github.com/keras-team/keras-nlp/pull/704
* Don't install tf stable when building our nightly image by mattdangerw in https://github.com/keras-team/keras-nlp/pull/711
* Add OPT Backbone and Tokenizer by mattdangerw in https://github.com/keras-team/keras-nlp/pull/699
* Small OPT Doc-string Edits by abheesht17 in https://github.com/keras-team/keras-nlp/pull/716
* Default compilation other classifiers by Plutone11011 in https://github.com/keras-team/keras-nlp/pull/714
* Add BartTokenizer and BART Presets by abheesht17 in https://github.com/keras-team/keras-nlp/pull/685
* Add an add_prefix_space Arg in BytePairTokenizer by shivance in https://github.com/keras-team/keras-nlp/pull/715
* Opt presets by mattdangerw in https://github.com/keras-team/keras-nlp/pull/707
* fix import of tensorflow_text in tf_utils by sampathweb in https://github.com/keras-team/keras-nlp/pull/723
* Check for masked token in roberta tokenizer by mattdangerw in https://github.com/keras-team/keras-nlp/pull/742
* Improve test coverage for special tokens in model tokenizers by mattdangerw in https://github.com/keras-team/keras-nlp/pull/743
* Fix the sampler truncation strategy by chenmoneygithub in https://github.com/keras-team/keras-nlp/pull/713
* Add ALBERT Conversion Script by abheesht17 in https://github.com/keras-team/keras-nlp/pull/736
* Add FNet Conversion Script by abheesht17 in https://github.com/keras-team/keras-nlp/pull/737
* Add BART Conversion Script by abheesht17 in https://github.com/keras-team/keras-nlp/pull/739
* Pass Correct LayerNorm Epsilon value to TransformerEncoder in Backbones by TheAthleticCoder in https://github.com/keras-team/keras-nlp/pull/731
* Improving the layer Description. by Neeshamraghav012 in https://github.com/keras-team/keras-nlp/pull/734
* Adding ragged support to SinePositionEncoding by apupneja in https://github.com/keras-team/keras-nlp/pull/751
* Fix trailing space by mattdangerw in https://github.com/keras-team/keras-nlp/pull/755
* Adding an AlbertMaskedLM task + Fix Projection layer dimension in MaskedLMHead by shivance in https://github.com/keras-team/keras-nlp/pull/725
* New docstring example for TokenAndPosition Embedding layer. by Neeshamraghav012 in https://github.com/keras-team/keras-nlp/pull/760
* Add a note for TPU issues for deberta_v3 by mattdangerw in https://github.com/keras-team/keras-nlp/pull/758
* Add missing exports to models API by mattdangerw in https://github.com/keras-team/keras-nlp/pull/763
* Autogenerate preset table by Cyber-Machine in https://github.com/keras-team/keras-nlp/pull/690
* Version bump to 0.5.0 by mattdangerw in https://github.com/keras-team/keras-nlp/pull/767
* Adding a FNetMaskedLM task model and preprocessor by apupneja in https://github.com/keras-team/keras-nlp/pull/740
* Add a DistilBertMaskedLM task model by ADITYADAS1999 in https://github.com/keras-team/keras-nlp/pull/724
* Add cache support to decoding journey by chenmoneygithub in https://github.com/keras-team/keras-nlp/pull/745
* Handle [MASK] token in DebertaV3Tokenizer by abheesht17 in https://github.com/keras-team/keras-nlp/pull/759
* Update README for 2.4.1 release by mattdangerw in https://github.com/keras-team/keras-nlp/pull/757
* Fix typo in test docstring by jbischof in https://github.com/keras-team/keras-nlp/pull/791
* Fixed Incorrect Links for FNet and DeBERTaV3 models by Cyber-Machine in https://github.com/keras-team/keras-nlp/pull/793
* Patch 1 - doc-string spell fix by atharvapurdue in https://github.com/keras-team/keras-nlp/pull/781
* Don't rely on core keras initializer config details by mattdangerw in https://github.com/keras-team/keras-nlp/pull/802
* Simplify the cache decoding graph by mattdangerw in https://github.com/keras-team/keras-nlp/pull/780
* Fix Fenced Doc-String 782 by atharvapurdue in https://github.com/keras-team/keras-nlp/pull/785
* Solve 721 Deberta masklm model by Plutone11011 in https://github.com/keras-team/keras-nlp/pull/732
* Add from_config to sampler by mattdangerw in https://github.com/keras-team/keras-nlp/pull/803
* BertMaskedLM Task Model and Preprocessor by Cyber-Machine in https://github.com/keras-team/keras-nlp/pull/774
* Stop generation once end_token_id is seen by chenmoneygithub in https://github.com/keras-team/keras-nlp/pull/769
* Added model card links for all pretrained models. by Cyber-Machine in https://github.com/keras-team/keras-nlp/pull/795
* Initial PR demonstrating public API export logic. by fchollet in https://github.com/keras-team/keras-nlp/pull/747
* Add preset for finetuning GPT2 on CNN news by chenmoneygithub in https://github.com/keras-team/keras-nlp/pull/807
* Add API exports for metrics documented on keras.io by shivance in https://github.com/keras-team/keras-nlp/pull/816
* Add API exports for samplers documented on keras.io by shivance in https://github.com/keras-team/keras-nlp/pull/815
* Add API exports for models documented on keras.io by shivance in https://github.com/keras-team/keras-nlp/pull/814
* Add API exports for tokenizers documented on keras.io by shivance in https://github.com/keras-team/keras-nlp/pull/817
* Add API exports for layers documented on keras.io by fchollet in https://github.com/keras-team/keras-nlp/pull/811
* Add keras_nlp.utils public API exports. by fchollet in https://github.com/keras-team/keras-nlp/pull/819
* retrained bert_tiny_uncased_en_sst2_training.ipynb by susnato in https://github.com/keras-team/keras-nlp/pull/771
* Temporary solution to avoid recompilation by chenmoneygithub in https://github.com/keras-team/keras-nlp/pull/808
* Call super.config() in BartBackbone's get_config() by shivance in https://github.com/keras-team/keras-nlp/pull/818
* Update typo in README.md by ADITYADAS1999 in https://github.com/keras-team/keras-nlp/pull/821
* Add Whisper Backbone by abheesht17 in https://github.com/keras-team/keras-nlp/pull/801
* Added note for tensorflow-text in the CONTRIBUTING guide by jaygala223 in https://github.com/keras-team/keras-nlp/pull/805
* Roadmap update by jaygala223 in https://github.com/keras-team/keras-nlp/pull/800
* Remove API export decorator from base classes by shivance in https://github.com/keras-team/keras-nlp/pull/824
* Move integration tests out of repo sources. by fchollet in https://github.com/keras-team/keras-nlp/pull/826
* Function merge_padding_and_attention_mask does not return an output with the desired shape when both padding and attention masks are given by abodinier in https://github.com/keras-team/keras-nlp/pull/790
* Adding XXBackboneTPUTests by shivance in https://github.com/keras-team/keras-nlp/pull/839
* Add a t5 tokenizer by mattdangerw in https://github.com/keras-team/keras-nlp/pull/852
* Add compilation defaults for the BertMaskedLM task model by ADITYADAS1999 in https://github.com/keras-team/keras-nlp/pull/836
* added __init__ file for t5 by Akorex in https://github.com/keras-team/keras-nlp/pull/853
* Modified Docstring for GPT2CasualLM by TheAthleticCoder in https://github.com/keras-team/keras-nlp/pull/855
* Rework bert docstrings for progressive disclosure of complexity by mattdangerw in https://github.com/keras-team/keras-nlp/pull/843
* Fix "causal" spelling in export decorator by abheesht17 in https://github.com/keras-team/keras-nlp/pull/861
* Default compilation for Albert, Distilbert, Roberta MaskedLM by shivance in https://github.com/keras-team/keras-nlp/pull/833
* Speed up default BERT testing roughly 3x by mattdangerw in https://github.com/keras-team/keras-nlp/pull/859
* Add compilation defaults for the Fnet MaskedLM task model by soma2000-lang in https://github.com/keras-team/keras-nlp/pull/834
* Default compilation for Debertav3MaskedLM model by Cyber-Machine in https://github.com/keras-team/keras-nlp/pull/835
* Remove from_preset from fnet tokenizer by mattdangerw in https://github.com/keras-team/keras-nlp/pull/865
* Add T5 backbone by fchollet in https://github.com/keras-team/keras-nlp/pull/828
* Speeding the tests for opt by susnato in https://github.com/keras-team/keras-nlp/pull/886
* Move generate compilation to the task model by mattdangerw in https://github.com/keras-team/keras-nlp/pull/804
* Speeding the tests for xlm_roberta by susnato in https://github.com/keras-team/keras-nlp/pull/885
* Rework DistilBERT docstrings for progressive disclosure of complexity. by Cyber-Machine in https://github.com/keras-team/keras-nlp/pull/881
* Speeding the tests for T5 by susnato in https://github.com/keras-team/keras-nlp/pull/888
* Rework OPT docstrings for progressive disclosure of complexity. by Warlord-K in https://github.com/keras-team/keras-nlp/pull/893
* Get our fenced docstring tests working again by mattdangerw in https://github.com/keras-team/keras-nlp/pull/895
* Speed up default RoBERTa testing roughly 3x by shivance in https://github.com/keras-team/keras-nlp/pull/897
* Speeding the tests for whisper by susnato in https://github.com/keras-team/keras-nlp/pull/887
* Update BytePairTokenizerCache to have similar dtypes for x and y in self.factors. by Sruinard in https://github.com/keras-team/keras-nlp/pull/871
* Init `_backbone`, `_tokenizer` and `_preprocessor` in Task by jbischof in https://github.com/keras-team/keras-nlp/pull/899
* Rework Whisper docstrings for progressive disclosure of complexity by susnato in https://github.com/keras-team/keras-nlp/pull/903
* Speed up default DeBERTa_v3 testing roughly 3x by TheAthleticCoder in https://github.com/keras-team/keras-nlp/pull/905
* Rework docstring of XLMRoberta by abuelnasr0 in https://github.com/keras-team/keras-nlp/pull/882
* Stripping the MASK token by TheAthleticCoder in https://github.com/keras-team/keras-nlp/pull/876
* Possible fix for task.summary() by mattdangerw in https://github.com/keras-team/keras-nlp/pull/901
* Speed up default FNet testing speedups. by Cyber-Machine in https://github.com/keras-team/keras-nlp/pull/894
* Added TPU test for DebertaV3Backbone by TheAthleticCoder in https://github.com/keras-team/keras-nlp/pull/924
* Fix failing TPU tests by chenmoneygithub in https://github.com/keras-team/keras-nlp/pull/931
* Add model contribution guide by abheesht17 in https://github.com/keras-team/keras-nlp/pull/820
* Resolved roberta_checkpoint by TheAthleticCoder in https://github.com/keras-team/keras-nlp/pull/874
* GLUE evaluation automation script by susnato in https://github.com/keras-team/keras-nlp/pull/848
* Ensure shape in sample so that the shape is correct after TFLite conversion by chenmoneygithub in https://github.com/keras-team/keras-nlp/pull/902
* Returning all Beams and Probs and adding a Testing Unit by TheAthleticCoder in https://github.com/keras-team/keras-nlp/pull/908
* Roberta docstring reworking by abuelnasr0 in https://github.com/keras-team/keras-nlp/pull/910
* Speeding the tests for Albert by soma2000-lang in https://github.com/keras-team/keras-nlp/pull/873
* Mlm mask generator docstring adding example by abuelnasr0 in https://github.com/keras-team/keras-nlp/pull/916
* Don't save traces for saved model by mattdangerw in https://github.com/keras-team/keras-nlp/pull/945
* Bump stable tf version to 2.12 by mattdangerw in https://github.com/keras-team/keras-nlp/pull/944
* Speeding the tests for DistilBert by soma2000-lang in https://github.com/keras-team/keras-nlp/pull/872
* Allow BPE to treat special tokens as one token by chenmoneygithub in https://github.com/keras-team/keras-nlp/pull/939
* Edit examples in samplers by abuelnasr0 in https://github.com/keras-team/keras-nlp/pull/957
* Add RandomSampler to Samplers by abuelnasr0 in https://github.com/keras-team/keras-nlp/pull/952
* Add BartPreprocessor by abheesht17 in https://github.com/keras-team/keras-nlp/pull/856
* Remove the old sampler utilities by mattdangerw in https://github.com/keras-team/keras-nlp/pull/948
* Use direct imports everywhere in library by mattdangerw in https://github.com/keras-team/keras-nlp/pull/961
* Update docstrings for relocated `sampler` arg by jbischof in https://github.com/keras-team/keras-nlp/pull/964
* Fix gpt2, t5 and fnet under mixed precision by mattdangerw in https://github.com/keras-team/keras-nlp/pull/958
* Small fixes for special_tokens arg in BPE by abheesht17 in https://github.com/keras-team/keras-nlp/pull/969
* Add contrastive sampler by chenmoneygithub in https://github.com/keras-team/keras-nlp/pull/896
* Mark num_classes as required in Classifier classes by chenmoneygithub in https://github.com/keras-team/keras-nlp/pull/971
* Rework model docstrings for progressive disclosure of complexity for f_net by ADITYADAS1999 in https://github.com/keras-team/keras-nlp/pull/879
* Handle OOV token in XLMRoBERTaTokenizer's token_to_id function by abheesht17 in https://github.com/keras-team/keras-nlp/pull/968
* Clean up the docker and lint setup by haifeng-jin in https://github.com/keras-team/keras-nlp/pull/981
* Update generate() to work like fit() and predict() by mattdangerw in https://github.com/keras-team/keras-nlp/pull/932
* Speed top-p sampler up by only sampling from top-k tokens by chenmoneygithub in https://github.com/keras-team/keras-nlp/pull/980
* Expose the generate_step compilable function by mattdangerw in https://github.com/keras-team/keras-nlp/pull/982
* Fix decoder inputs in BART preprocessor by abheesht17 in https://github.com/keras-team/keras-nlp/pull/984
* Convert string tensors to python strings in `generate()` by mattdangerw in https://github.com/keras-team/keras-nlp/pull/983
* Adding a temperature argument to the base sampler class and related tests by TheAthleticCoder in https://github.com/keras-team/keras-nlp/pull/951
* Track the task preprocessor layer as part of model by mattdangerw in https://github.com/keras-team/keras-nlp/pull/985
* Add an XLMRobertaMaskedLM task model by shivance in https://github.com/keras-team/keras-nlp/pull/950
* Add an activation argument to all classifiers by mattdangerw in https://github.com/keras-team/keras-nlp/pull/991
* Remove activation from README quickstart by mattdangerw in https://github.com/keras-team/keras-nlp/pull/992
* Rework albert docstrings by mattdangerw in https://github.com/keras-team/keras-nlp/pull/993
* Rework bart docstrings by mattdangerw in https://github.com/keras-team/keras-nlp/pull/994
* Rework deberta docstrings by mattdangerw in https://github.com/keras-team/keras-nlp/pull/995
* Misc fixes to docstrings by mattdangerw in https://github.com/keras-team/keras-nlp/pull/996
* Added temperature argument to the Contrastive Sampler by TheAthleticCoder in https://github.com/keras-team/keras-nlp/pull/997
* Add `OPTCausalLM` and preprocessors by chenmoneygithub in https://github.com/keras-team/keras-nlp/pull/990
* Version bump to 0.5.0.dev0 by chenmoneygithub in https://github.com/keras-team/keras-nlp/pull/1002
* Add a flag to restrict which docstring tests run by mattdangerw in https://github.com/keras-team/keras-nlp/pull/999
* fix docstring for 0.5 release by chenmoneygithub in https://github.com/keras-team/keras-nlp/pull/1005
* Serialize activation fn properly by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1007
* Try adding an error if activation and loss are mismatched by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1008
* Fix docstring for 0.5 release by chenmoneygithub in https://github.com/keras-team/keras-nlp/pull/1009
* Switch to using pip_build for release by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1011
* Make version number SSoT. by fchollet in https://github.com/keras-team/keras-nlp/pull/827
* Add DTensor layout map class method for OPT by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1000
* Add DTensor layout map class method for GPT-2 by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1014
* Standalone functions for generate pre/post processing for GPT-2 by mattdangerw in https://github.com/keras-team/keras-nlp/pull/998
* install namex in the publish workflow by chenmoneygithub in https://github.com/keras-team/keras-nlp/pull/1020
* Update publish-to-pypi.yml by chenmoneygithub in https://github.com/keras-team/keras-nlp/pull/1021
* Standalone functions for generate pre/post processing for OPT by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1015

New Contributors
* haifeng-jin made their first contribution in https://github.com/keras-team/keras-nlp/pull/618
* mbrukman made their first contribution in https://github.com/keras-team/keras-nlp/pull/628
* soma2000-lang made their first contribution in https://github.com/keras-team/keras-nlp/pull/665
* NusretOzates made their first contribution in https://github.com/keras-team/keras-nlp/pull/664
* shivance made their first contribution in https://github.com/keras-team/keras-nlp/pull/673
* Plutone11011 made their first contribution in https://github.com/keras-team/keras-nlp/pull/714
* TheAthleticCoder made their first contribution in https://github.com/keras-team/keras-nlp/pull/731
* Neeshamraghav012 made their first contribution in https://github.com/keras-team/keras-nlp/pull/734
* apupneja made their first contribution in https://github.com/keras-team/keras-nlp/pull/751
* Cyber-Machine made their first contribution in https://github.com/keras-team/keras-nlp/pull/690
* atharvapurdue made their first contribution in https://github.com/keras-team/keras-nlp/pull/781
* fchollet made their first contribution in https://github.com/keras-team/keras-nlp/pull/747
* susnato made their first contribution in https://github.com/keras-team/keras-nlp/pull/771
* jaygala223 made their first contribution in https://github.com/keras-team/keras-nlp/pull/805
* abodinier made their first contribution in https://github.com/keras-team/keras-nlp/pull/790
* Akorex made their first contribution in https://github.com/keras-team/keras-nlp/pull/853
* Warlord-K made their first contribution in https://github.com/keras-team/keras-nlp/pull/893
* Sruinard made their first contribution in https://github.com/keras-team/keras-nlp/pull/871
* abuelnasr0 made their first contribution in https://github.com/keras-team/keras-nlp/pull/882

**Full Changelog**: https://github.com/keras-team/keras-nlp/compare/v0.4.0...v0.5.0

The 0.4.1 release is a minor release with new model architectures and compilation defaults for task models. If you encounter any problems or have questions, please open an issue!

Summary
* Added compilation defaults for all **task** models (e.g. `keras_nlp.models.BertClassifier`). No existing functionality is changed, but users of task models can now skip calling `.compile()` and use default learning rates and optimization strategies provided by the library.
* Added `keras_nlp.models.AlbertBackbone`, `keras_nlp.models.AlbertClassifier`, preprocessor, and tokenizer layers for pre-trained [ALBERT](https://arxiv.org/abs/1909.11942) models.
* Added `keras_nlp.models.FNetBackbone`, `keras_nlp.models.FNetClassifier`, preprocessor, and tokenizer layers for pre-trained [FNet](https://arxiv.org/abs/2105.03824) models.
* Added `keras_nlp.models.DebertaV3Backbone`, `keras_nlp.models.DebertaV3Classifier`, preprocessor, and tokenizer layers for pre-trained [DeBERTaV3](https://arxiv.org/abs/2111.09543) models.

What's Changed
* Update python version in readme to 3.8 by haifeng-jin in https://github.com/keras-team/keras-nlp/pull/618
* Modify our pip install line so we upgrade tf by mattdangerw in https://github.com/keras-team/keras-nlp/pull/616
* Use Adam optimizer for quick start by mattdangerw in https://github.com/keras-team/keras-nlp/pull/620
* Clean up class name and `self` in calls to `super()` by mbrukman in https://github.com/keras-team/keras-nlp/pull/628
* Update word_piece_tokenizer.py by ADITYADAS1999 in https://github.com/keras-team/keras-nlp/pull/617
* Add DeBERTaV3 Conversion Script by abheesht17 in https://github.com/keras-team/keras-nlp/pull/633
* Add AlbertTokenizer and AlbertPreprocessor by abheesht17 in https://github.com/keras-team/keras-nlp/pull/627
* Create `Backbone` base class by jbischof in https://github.com/keras-team/keras-nlp/pull/621
* Add TPU testing by chenmoneygithub in https://github.com/keras-team/keras-nlp/pull/591
* Add Base Preprocessor Class by abheesht17 in https://github.com/keras-team/keras-nlp/pull/638
* Add keras_nlp.samplers by chenmoneygithub in https://github.com/keras-team/keras-nlp/pull/563
* Add ALBERT Backbone by abheesht17 in https://github.com/keras-team/keras-nlp/pull/622
* Add a small script to count parameters in our presets by mattdangerw in https://github.com/keras-team/keras-nlp/pull/610
* Clean up examples/ directory by ADITYADAS1999 in https://github.com/keras-team/keras-nlp/pull/637
* Fix Small BERT Typo by abheesht17 in https://github.com/keras-team/keras-nlp/pull/651
* Rename examples/bert -> examples/bert_pretraining by mattdangerw in https://github.com/keras-team/keras-nlp/pull/647
* Add FNet Preprocessor by abheesht17 in https://github.com/keras-team/keras-nlp/pull/646
* Add FNet Backbone by abheesht17 in https://github.com/keras-team/keras-nlp/pull/643
* Small DeBERTa Docstring Fixes by abheesht17 in https://github.com/keras-team/keras-nlp/pull/666
* Add Fenced Docstring Testing by abheesht17 in https://github.com/keras-team/keras-nlp/pull/640
* Corrected the epsilon value by soma2000-lang in https://github.com/keras-team/keras-nlp/pull/665
* Consolidate docstring formatting weirdness in Backbone and Preprocessor base classes by mattdangerw in https://github.com/keras-team/keras-nlp/pull/654
* Fix `value_dim` in `TransformerDecoder`'s cross-attn layer by abheesht17 in https://github.com/keras-team/keras-nlp/pull/667
* Add ALBERT Presets by abheesht17 in https://github.com/keras-team/keras-nlp/pull/655
* Add Base Task Class by abheesht17 in https://github.com/keras-team/keras-nlp/pull/671
* Implement TopP, TopK and Beam samplers by chenmoneygithub in https://github.com/keras-team/keras-nlp/pull/652
* Add FNet Presets by abheesht17 in https://github.com/keras-team/keras-nlp/pull/659
* Bump the year to 2023 by mattdangerw in https://github.com/keras-team/keras-nlp/pull/679
* Add BART Backbone by abheesht17 in https://github.com/keras-team/keras-nlp/pull/661
* Handle trainable and name in the backbone base class by mattdangerw in https://github.com/keras-team/keras-nlp/pull/680
* Ignore Task Docstring for Testing by abheesht17 in https://github.com/keras-team/keras-nlp/pull/683
* Light-weight benchmarking script by NusretOzates in https://github.com/keras-team/keras-nlp/pull/664
* Conditionally import tf_text everywhere by mattdangerw in https://github.com/keras-team/keras-nlp/pull/684
* Expose `token_embedding` as a Backbone Property by abheesht17 in https://github.com/keras-team/keras-nlp/pull/676
* Move `from_preset` to base tokenizer classes by shivance in https://github.com/keras-team/keras-nlp/pull/673
* add f_net_classifier and f_net_classifier_test by ADITYADAS1999 in https://github.com/keras-team/keras-nlp/pull/670
* import rouge_scorer directly from rouge_score package by sampathweb in https://github.com/keras-team/keras-nlp/pull/691
* Fix typo in requirements file juypter -> jupyter by mattdangerw in https://github.com/keras-team/keras-nlp/pull/693
* Temporary fix to get nightly green again by mattdangerw in https://github.com/keras-team/keras-nlp/pull/696
* GPT2 Text Generation APIs by chenmoneygithub in https://github.com/keras-team/keras-nlp/pull/592
* Run keras saving tests on nightly and fix RobertaClassifier test by mattdangerw in https://github.com/keras-team/keras-nlp/pull/692
* Speed up pip install keras-nlp; simplify deps by mattdangerw in https://github.com/keras-team/keras-nlp/pull/697
* Add `AlbertClassifier` by shivance in https://github.com/keras-team/keras-nlp/pull/668
* Make tokenizer, backbone, preprocessor properties settable on base class by mattdangerw in https://github.com/keras-team/keras-nlp/pull/700
* Update to latest black by mattdangerw in https://github.com/keras-team/keras-nlp/pull/708
* RobertaMaskedLM task and preprocessor by mattdangerw in https://github.com/keras-team/keras-nlp/pull/653
* Default compilation for BERT/RoBERTa classifiers by jbischof in https://github.com/keras-team/keras-nlp/pull/695
* Add start/end token padding to `GPT2Preprocessor` by chenmoneygithub in https://github.com/keras-team/keras-nlp/pull/704
* Don't install tf stable when building our nightly image by mattdangerw in https://github.com/keras-team/keras-nlp/pull/711
* Add OPT Backbone and Tokenizer by mattdangerw in https://github.com/keras-team/keras-nlp/pull/699
* Small OPT Doc-string Edits by abheesht17 in https://github.com/keras-team/keras-nlp/pull/716
* Default compilation other classifiers by Plutone11011 in https://github.com/keras-team/keras-nlp/pull/714
* Add BartTokenizer and BART Presets by abheesht17 in https://github.com/keras-team/keras-nlp/pull/685
* Add an add_prefix_space Arg in BytePairTokenizer by shivance in https://github.com/keras-team/keras-nlp/pull/715
* Opt presets by mattdangerw in https://github.com/keras-team/keras-nlp/pull/707
* fix import of tensorflow_text in tf_utils by sampathweb in https://github.com/keras-team/keras-nlp/pull/723
* Check for masked token in roberta tokenizer by mattdangerw in https://github.com/keras-team/keras-nlp/pull/742
* Improve test coverage for special tokens in model tokenizers by mattdangerw in https://github.com/keras-team/keras-nlp/pull/743
* Fix the sampler truncation strategy by chenmoneygithub in https://github.com/keras-team/keras-nlp/pull/713
* Add ALBERT Conversion Script by abheesht17 in https://github.com/keras-team/keras-nlp/pull/736
* Add FNet Conversion Script by abheesht17 in https://github.com/keras-team/keras-nlp/pull/737
* Add BART Conversion Script by abheesht17 in https://github.com/keras-team/keras-nlp/pull/739
* Pass Correct LayerNorm Epsilon value to TransformerEncoder in Backbones by TheAthleticCoder in https://github.com/keras-team/keras-nlp/pull/731
* Improving the layer Description. by Neeshamraghav012 in https://github.com/keras-team/keras-nlp/pull/734
* Adding ragged support to SinePositionEncoding by apupneja in https://github.com/keras-team/keras-nlp/pull/751
* Fix trailing space by mattdangerw in https://github.com/keras-team/keras-nlp/pull/755
* Adding an AlbertMaskedLM task model and preprocessor by shivance in https://github.com/keras-team/keras-nlp/pull/725
* New docstring example for TokenAndPosition Embedding layer. by Neeshamraghav012 in https://github.com/keras-team/keras-nlp/pull/760
* Add a note for TPU issues for deberta_v3 by mattdangerw in https://github.com/keras-team/keras-nlp/pull/758
* Add missing exports to models API by mattdangerw in https://github.com/keras-team/keras-nlp/pull/763
* Autogenerate preset table by Cyber-Machine in https://github.com/keras-team/keras-nlp/pull/690
* Remove work in progress API for 0.4.1 release by mattdangerw in https://github.com/keras-team/keras-nlp/pull/765
* Version bump to 0.4.1.dev0 by mattdangerw in https://github.com/keras-team/keras-nlp/pull/766
* Version bump to 0.4.1 by mattdangerw in https://github.com/keras-team/keras-nlp/pull/768

New Contributors
* haifeng-jin made their first contribution in https://github.com/keras-team/keras-nlp/pull/618
* mbrukman made their first contribution in https://github.com/keras-team/keras-nlp/pull/628
* soma2000-lang made their first contribution in https://github.com/keras-team/keras-nlp/pull/665
* NusretOzates made their first contribution in https://github.com/keras-team/keras-nlp/pull/664
* shivance made their first contribution in https://github.com/keras-team/keras-nlp/pull/673
* Plutone11011 made their first contribution in https://github.com/keras-team/keras-nlp/pull/714
* TheAthleticCoder made their first contribution in https://github.com/keras-team/keras-nlp/pull/731
* Neeshamraghav012 made their first contribution in https://github.com/keras-team/keras-nlp/pull/734
* Cyber-Machine made their first contribution in https://github.com/keras-team/keras-nlp/pull/690

**Full Changelog**: https://github.com/keras-team/keras-nlp/compare/v0.4.0...v0.4.1

Summary
* Dev release to test out the upcoming 0.4.1.

What's Changed
* Update python version in readme to 3.8 by haifeng-jin in https://github.com/keras-team/keras-nlp/pull/618
* Modify our pip install line so we upgrade tf by mattdangerw in https://github.com/keras-team/keras-nlp/pull/616
* Use Adam optimizer for quick start by mattdangerw in https://github.com/keras-team/keras-nlp/pull/620
* Clean up class name and `self` in calls to `super()` by mbrukman in https://github.com/keras-team/keras-nlp/pull/628
* Update word_piece_tokenizer.py by ADITYADAS1999 in https://github.com/keras-team/keras-nlp/pull/617
* Add DeBERTaV3 Conversion Script by abheesht17 in https://github.com/keras-team/keras-nlp/pull/633
* Add AlbertTokenizer and AlbertPreprocessor by abheesht17 in https://github.com/keras-team/keras-nlp/pull/627
* Create `Backbone` base class by jbischof in https://github.com/keras-team/keras-nlp/pull/621
* Add TPU testing by chenmoneygithub in https://github.com/keras-team/keras-nlp/pull/591
* Add Base Preprocessor Class by abheesht17 in https://github.com/keras-team/keras-nlp/pull/638
* Add keras_nlp.samplers by chenmoneygithub in https://github.com/keras-team/keras-nlp/pull/563
* Add ALBERT Backbone by abheesht17 in https://github.com/keras-team/keras-nlp/pull/622
* Add a small script to count parameters in our presets by mattdangerw in https://github.com/keras-team/keras-nlp/pull/610
* Clean up examples/ directory by ADITYADAS1999 in https://github.com/keras-team/keras-nlp/pull/637
* Fix Small BERT Typo by abheesht17 in https://github.com/keras-team/keras-nlp/pull/651
* Rename examples/bert -> examples/bert_pretraining by mattdangerw in https://github.com/keras-team/keras-nlp/pull/647
* Add FNet Preprocessor by abheesht17 in https://github.com/keras-team/keras-nlp/pull/646
* Add FNet Backbone by abheesht17 in https://github.com/keras-team/keras-nlp/pull/643
* Small DeBERTa Docstring Fixes by abheesht17 in https://github.com/keras-team/keras-nlp/pull/666
* Add Fenced Docstring Testing by abheesht17 in https://github.com/keras-team/keras-nlp/pull/640
* Corrected the epsilon value by soma2000-lang in https://github.com/keras-team/keras-nlp/pull/665
* Consolidate docstring formatting weirdness in Backbone and Preprocessor base classes by mattdangerw in https://github.com/keras-team/keras-nlp/pull/654
* Fix `value_dim` in `TransformerDecoder`'s cross-attn layer by abheesht17 in https://github.com/keras-team/keras-nlp/pull/667
* Add ALBERT Presets by abheesht17 in https://github.com/keras-team/keras-nlp/pull/655
* Add Base Task Class by abheesht17 in https://github.com/keras-team/keras-nlp/pull/671
* Implement TopP, TopK and Beam samplers by chenmoneygithub in https://github.com/keras-team/keras-nlp/pull/652
* Add FNet Presets by abheesht17 in https://github.com/keras-team/keras-nlp/pull/659
* Bump the year to 2023 by mattdangerw in https://github.com/keras-team/keras-nlp/pull/679
* Add BART Backbone by abheesht17 in https://github.com/keras-team/keras-nlp/pull/661
* Handle trainable and name in the backbone base class by mattdangerw in https://github.com/keras-team/keras-nlp/pull/680
* Ignore Task Docstring for Testing by abheesht17 in https://github.com/keras-team/keras-nlp/pull/683
* Light-weight benchmarking script by NusretOzates in https://github.com/keras-team/keras-nlp/pull/664
* Conditionally import tf_text everywhere by mattdangerw in https://github.com/keras-team/keras-nlp/pull/684
* Expose `token_embedding` as a Backbone Property by abheesht17 in https://github.com/keras-team/keras-nlp/pull/676
* Move `from_preset` to base tokenizer classes by shivance in https://github.com/keras-team/keras-nlp/pull/673
* add f_net_classifier and f_net_classifier_test by ADITYADAS1999 in https://github.com/keras-team/keras-nlp/pull/670
* import rouge_scorer directly from rouge_score package by sampathweb in https://github.com/keras-team/keras-nlp/pull/691
* Fix typo in requirements file juypter -> jupyter by mattdangerw in https://github.com/keras-team/keras-nlp/pull/693
* Temporary fix to get nightly green again by mattdangerw in https://github.com/keras-team/keras-nlp/pull/696
* GPT2 Text Generation APIs by chenmoneygithub in https://github.com/keras-team/keras-nlp/pull/592
* Run keras saving tests on nightly and fix RobertaClassifier test by mattdangerw in https://github.com/keras-team/keras-nlp/pull/692
* Speed up pip install keras-nlp; simplify deps by mattdangerw in https://github.com/keras-team/keras-nlp/pull/697
* Add `AlbertClassifier` by shivance in https://github.com/keras-team/keras-nlp/pull/668
* Make tokenizer, backbone, preprocessor properties settable on base class by mattdangerw in https://github.com/keras-team/keras-nlp/pull/700
* Update to latest black by mattdangerw in https://github.com/keras-team/keras-nlp/pull/708
* RobertaMaskedLM task and preprocessor by mattdangerw in https://github.com/keras-team/keras-nlp/pull/653
* Default compilation for BERT/RoBERTa classifiers by jbischof in https://github.com/keras-team/keras-nlp/pull/695
* Add start/end token padding to `GPT2Preprocessor` by chenmoneygithub in https://github.com/keras-team/keras-nlp/pull/704
* Don't install tf stable when building our nightly image by mattdangerw in https://github.com/keras-team/keras-nlp/pull/711
* Add OPT Backbone and Tokenizer by mattdangerw in https://github.com/keras-team/keras-nlp/pull/699
* Small OPT Doc-string Edits by abheesht17 in https://github.com/keras-team/keras-nlp/pull/716
* Default compilation other classifiers by Plutone11011 in https://github.com/keras-team/keras-nlp/pull/714
* Add BartTokenizer and BART Presets by abheesht17 in https://github.com/keras-team/keras-nlp/pull/685
* Add an add_prefix_space Arg in BytePairTokenizer by shivance in https://github.com/keras-team/keras-nlp/pull/715
* Opt presets by mattdangerw in https://github.com/keras-team/keras-nlp/pull/707
* fix import of tensorflow_text in tf_utils by sampathweb in https://github.com/keras-team/keras-nlp/pull/723
* Check for masked token in roberta tokenizer by mattdangerw in https://github.com/keras-team/keras-nlp/pull/742
* Improve test coverage for special tokens in model tokenizers by mattdangerw in https://github.com/keras-team/keras-nlp/pull/743
* Fix the sampler truncation strategy by chenmoneygithub in https://github.com/keras-team/keras-nlp/pull/713
* Add ALBERT Conversion Script by abheesht17 in https://github.com/keras-team/keras-nlp/pull/736
* Add FNet Conversion Script by abheesht17 in https://github.com/keras-team/keras-nlp/pull/737
* Add BART Conversion Script by abheesht17 in https://github.com/keras-team/keras-nlp/pull/739
* Pass Correct LayerNorm Epsilon value to TransformerEncoder in Backbones by TheAthleticCoder in https://github.com/keras-team/keras-nlp/pull/731
* Improving the layer Description. by Neeshamraghav012 in https://github.com/keras-team/keras-nlp/pull/734
* Adding ragged support to SinePositionEncoding by apupneja in https://github.com/keras-team/keras-nlp/pull/751
* Fix trailing space by mattdangerw in https://github.com/keras-team/keras-nlp/pull/755
* Adding an AlbertMaskedLM task model and preprocessor by shivance in https://github.com/keras-team/keras-nlp/pull/725
* New docstring example for TokenAndPosition Embedding layer. by Neeshamraghav012 in https://github.com/keras-team/keras-nlp/pull/760
* Add a note for TPU issues for deberta_v3 by mattdangerw in https://github.com/keras-team/keras-nlp/pull/758
* Add missing exports to models API by mattdangerw in https://github.com/keras-team/keras-nlp/pull/763
* Autogenerate preset table by Cyber-Machine in https://github.com/keras-team/keras-nlp/pull/690
* Version bump to 0.5.0 by mattdangerw in https://github.com/keras-team/keras-nlp/pull/767

New Contributors
* haifeng-jin made their first contribution in https://github.com/keras-team/keras-nlp/pull/618
* mbrukman made their first contribution in https://github.com/keras-team/keras-nlp/pull/628
* soma2000-lang made their first contribution in https://github.com/keras-team/keras-nlp/pull/665
* NusretOzates made their first contribution in https://github.com/keras-team/keras-nlp/pull/664
* shivance made their first contribution in https://github.com/keras-team/keras-nlp/pull/673
* Plutone11011 made their first contribution in https://github.com/keras-team/keras-nlp/pull/714
* TheAthleticCoder made their first contribution in https://github.com/keras-team/keras-nlp/pull/731
* Neeshamraghav012 made their first contribution in https://github.com/keras-team/keras-nlp/pull/734
* apupneja made their first contribution in https://github.com/keras-team/keras-nlp/pull/751
* Cyber-Machine made their first contribution in https://github.com/keras-team/keras-nlp/pull/690

**Full Changelog**: https://github.com/keras-team/keras-nlp/compare/v0.4.0...v0.4.1.dev0