Keras-nlp

Summary
* Short names for shield gemma checkpoints.
python
keras_nlp.models.GemmaCausalLM.from_preset("shieldgemma_2b_en")


What's Changed
* Version bump dev release by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1732
* Version bump for release by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1733


**Full Changelog**: https://github.com/keras-team/keras-nlp/compare/v0.14.2...v0.14.3

Summary

* Add Gemma 2 2b.
* Fixes for logit softcapping.

What's Changed
* Version bump 0.14.2.dev0 by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1719
* Bump pypi action version by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1722
* version bump by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1723
* Version bump 0.14.2 by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1724


**Full Changelog**: https://github.com/keras-team/keras-nlp/compare/v0.14.1...v0.14.2

Summary

* Update Gemma 2 9b to fix minor config error.

What's Changed
* Bump version to fix query norm in Gemma 2 9b by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1709
* Version bump 0.14.1.dev0 by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1714

**Full Changelog**: https://github.com/keras-team/keras-nlp/compare/v0.14.0...v0.14.1

Summary
* Add Gemma 2 model!
* Support loading fine-tuned transformers checkpoints in KerasNLP. Loading Gemma and Llama3 models are supported for now and will convert on the fly.
* KerasNLP no longer supports Keras 2. Read [Getting started](https://keras.io/getting_started/) with Keras for more information on installing Keras 3 and compatibility with different frameworks. We recommend using KerasNLP with TensorFlow 2.16 or later, as TF 2.16 packages Keras 3 by default.

What's Changed
* Fix newline characters for pali_gemma by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1655
* Remove dead code by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1659
* Fix some testing on the latest version of keras by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1663
* Vicuna Models checkpoints transfer script by sineeli in https://github.com/keras-team/keras-nlp/pull/1657
* Add documented but missing methods for some tokenizers by SamanehSaadat in https://github.com/keras-team/keras-nlp/pull/1664
* Changed from_preset file downloading to use GFile when able by VarunS1997 in https://github.com/keras-team/keras-nlp/pull/1665
* Fix gfile downloads by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1666
* More error handling for gfile by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1667
* Update error message by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1668
* Ditch Keras 2 support by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1658
* fix GemmaBackbone.get_layout_map + test by martin-gorner in https://github.com/keras-team/keras-nlp/pull/1669
* Covert a `safetensor` checkpoint from Hugging Face hub by ariG23498 in https://github.com/keras-team/keras-nlp/pull/1662
* Add Gemma 2 model by grasskin in https://github.com/keras-team/keras-nlp/pull/1673
* Version bump to 0.14.0.dev0 by grasskin in https://github.com/keras-team/keras-nlp/pull/1677


**Full Changelog**: https://github.com/keras-team/keras-nlp/compare/v0.12.1...r0.14

Summary

* ⚠️ PaliGemma includes rescaling by default, so images are expected to be passed in the `[0, 255]` range. This is a backward incompatible change with the original release. Restore the original behavior as follows:
python
keras_nlp.models.PaliGemmaBackbone.from_preset(
"pali_gemma_3b_224",
include_rescaling=False,
)

* Released the Falcon model.

What's Changed
* Update version to 0.13.0 for the master branch by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1640
* Update llama3 preset versions by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1641
* extra argument in save_to_preset method by sineeli in https://github.com/keras-team/keras-nlp/pull/1634
* Fix a typo in an error handling message by SamanehSaadat in https://github.com/keras-team/keras-nlp/pull/1647
* Fix a typo in phi3 metadata by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1646
* Add `FalconCausalLM` by SamanehSaadat in https://github.com/keras-team/keras-nlp/pull/1635
* Add include rescaling to the pali gemma backbone by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1650
* PaliGemma docstring fix by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1651
* Version bump for 0.12.0.dev0 by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1652
* Version bump 0.12.1 by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1653

New Contributors
* sineeli made their first contribution in https://github.com/keras-team/keras-nlp/pull/1634

**Full Changelog**: https://github.com/keras-team/keras-nlp/compare/v0.12.0...v0.12.1

Summary
Add [PaliGemma](https://www.kaggle.com/models/keras/paligemma), [Llama 3](https://www.kaggle.com/models/keras/llama3), and [Phi 3](https://www.kaggle.com/models/keras/phi3) models.

PaliGemma quickstart, see [a complete usage on Kaggle](https://www.kaggle.com/models/keras/paligemma/keras/pali_gemma_3b_224).
python
pali_gemma_lm = keras_nlp.models.PaliGemmaCausalLM.from_preset(
"pali_gemma_3b_224"
)
pali_gemma_lm.generate(
inputs={
"images": images,
"prompts": prompts,
}
)

What's Changed
* Add CodeGemma 1.1 presets by grasskin in https://github.com/keras-team/keras-nlp/pull/1617
* Fix rope scaling factor by abuelnasr0 in https://github.com/keras-team/keras-nlp/pull/1605
* Fix the issue of propagating `training` argument in subclasses by james77777778 in https://github.com/keras-team/keras-nlp/pull/1623
* Pass kwargs to tokenizer when creating preprocessor by SamanehSaadat in https://github.com/keras-team/keras-nlp/pull/1632
* Add phi3 by abuelnasr0 in https://github.com/keras-team/keras-nlp/pull/1597
* Add LLaMA 3 tokenizer and preset by tirthasheshpatel in https://github.com/keras-team/keras-nlp/pull/1584
* Export missing llama 3 symbol by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1633
* PaliGemma by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1636
* Update pali_gemma_presets.py by divyashreepathihalli in https://github.com/keras-team/keras-nlp/pull/1637
* Update version to 0.13.0 for the master branch by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1640
* Update llama3 preset versions by mattdangerw in https://github.com/keras-team/keras-nlp/pull/1641


**Full Changelog**: https://github.com/keras-team/keras-nlp/compare/v0.11.1...v0.12.0