Merge branch 'keras-team:master' into falcon-causallm

.github/workflows/actions.yml

@@ -104,3 +104,12 @@ jobs:
           pip install --no-deps -e "." --progress-bar off
       - name: Lint
         run: bash shell/lint.sh
+      - name: Check for API changes
+        run: |
+          bash shell/api_gen.sh
+          git status
+          clean=$(git status | grep "nothing to commit")
+          if [ -z "$clean" ]; then
+            echo "Please run shell/api_gen.sh to generate API."
+            exit 1
+          fi

.kokoro/github/ubuntu/gpu/build.sh

@@ -57,6 +57,7 @@ then
 fi
 
 pip install --no-deps -e "." --progress-bar off
+pip install huggingface_hub
 
 # Run Extra Large Tests for Continuous builds
 if [ "${RUN_XLARGE:-0}" == "1" ]

CONTRIBUTING.md

@@ -117,13 +117,13 @@ has cuda support.
 conda create -y -n keras-nlp-cpu python=3.10
 conda activate keras-nlp-cpu
 pip install -r requirements.txt  # install deps
-python pip_build.py --install  # install keras-nlp
+pip install -e .  # install keras-nlp
 
 for backend in "jax" "torch" "tensorflow"; do
     conda create -y -n keras-nlp-${backend} python=3.10
     conda activate keras-nlp-${backend}
     pip install -r requirements-${backend}-cuda.txt  # install deps
-    python pip_build.py --install  # install keras-nlp
+    pip install -e .  # install keras-nlp
 done
 ```
 
@@ -158,6 +158,15 @@ This is automatically done if you clone using git inside WSL.
 Note that will not support Windows Shell/PowerShell for any scripts in this
 repository.
 
+## Update Public API
+
+Run API generation script when creating PRs that update `keras_nlp_export`
+public APIs. Add the files changed in `keras_nlp/api` to the same PR.
+
+```
+./shell/api_gen.sh
+```
+
 ## Testing changes
 
 KerasNLP is tested using [PyTest](https://docs.pytest.org/en/6.2.x/).

README.md

@@ -1,25 +1,27 @@
-# KerasNLP: Modular NLP Workflows for Keras
+# KerasNLP: Multi-framework NLP Models
 [![](https://github.com/keras-team/keras-nlp/workflows/Tests/badge.svg?branch=master)](https://github.com/keras-team/keras-nlp/actions?query=workflow%3ATests+branch%3Amaster)
 ![Python](https://img.shields.io/badge/python-v3.9.0+-success.svg)
 [![contributions welcome](https://img.shields.io/badge/contributions-welcome-brightgreen.svg?style=flat)](https://github.com/keras-team/keras-nlp/issues)
 
 KerasNLP is a natural language processing library that works natively
-with TensorFlow, JAX, or PyTorch. Built on Keras 3, these models, layers,
-metrics, and tokenizers can be trained and serialized in any framework and
-re-used in another without costly migrations.
-
-KerasNLP supports users through their entire development cycle. Our workflows
-are built from modular components that have state-of-the-art preset weights when
-used out-of-the-box and are easily customizable when more control is needed.
+with TensorFlow, JAX, or PyTorch. KerasNLP provides a repository of pre-trained
+models and a collection of lower-level building blocks for language modeling.
+Built on Keras 3, models can be trained and serialized in any framework
+and re-used in another without costly migrations.
 
 This library is an extension of the core Keras API; all high-level modules are
-[`Layers`](https://keras.io/api/layers/) or
-[`Models`](https://keras.io/api/models/) that receive that same level of polish
-as core Keras. If you are familiar with Keras, congratulations! You already
-understand most of KerasNLP.
-
-See our [Getting Started guide](https://keras.io/guides/keras_nlp/getting_started)
-to start learning our API. We welcome [contributions](CONTRIBUTING.md).
+Layers and Models that receive that same level of polish as core Keras.
+If you are familiar with Keras, congratulations! You already understand most of
+KerasNLP.
+
+All models support JAX, TensorFlow, and PyTorch from a single model
+definition and can be fine-tuned on GPUs and TPUs out of the box. Models can
+be trained on individual accelerators with built-in PEFT techniques, or
+fine-tuned at scale with model and data parallel training. See our
+[Getting Started guide](https://keras.io/guides/keras_nlp/getting_started)
+to start learning our API. Browse our models on
+[Kaggle](https://www.kaggle.com/organizations/keras/models).
+We welcome contributions.
 
 ## Quick Links
 
@@ -28,7 +30,7 @@ to start learning our API. We welcome [contributions](CONTRIBUTING.md).
 - [Home Page](https://keras.io/keras_nlp)
 - [Developer Guides](https://keras.io/guides/keras_nlp)
 - [API Reference](https://keras.io/api/keras_nlp)
-- [Getting Started guide](https://keras.io/guides/keras_nlp/getting_started) 
+- [Pre-trained Models](https://www.kaggle.com/organizations/keras/models)
 
 ### For contributors
 
@@ -38,53 +40,13 @@ to start learning our API. We welcome [contributions](CONTRIBUTING.md).
 - [API Design Guide](API_DESIGN_GUIDE.md)
 - [Call for Contributions](https://github.com/keras-team/keras-nlp/issues?q=is%3Aissue+is%3Aopen+label%3A%22contributions+welcome%22)
 
-## Installation
-
-KerasNLP supports both Keras 2 and Keras 3. We recommend Keras 3 for all new
-users, as it enables using KerasNLP models and layers with JAX, TensorFlow and
-PyTorch.
-
-### Keras 2 Installation
-
-To install the latest KerasNLP release with Keras 2, simply run:
-
-```
-pip install --upgrade keras-nlp
-```
-
-### Keras 3 Installation
-
-There are currently two ways to install Keras 3 with KerasNLP. To install the
-stable versions of KerasNLP and Keras 3, you should install Keras 3 **after**
-installing KerasNLP. This is a temporary step while TensorFlow is pinned to
-Keras 2, and will no longer be necessary after TensorFlow 2.16.
-
-```
-pip install --upgrade keras-nlp
-pip install --upgrade keras>=3
-```
-
-To install the latest nightly changes for both KerasNLP and Keras, you can use
-our nightly package.
-
-```
-pip install --upgrade keras-nlp-nightly
-```
-
-> [!IMPORTANT]
-> Keras 3 will not function with TensorFlow 2.14 or earlier.
-
-Read [Getting started with Keras](https://keras.io/getting_started/) for more information
-on installing Keras 3 and compatibility with different frameworks.
-
 ## Quickstart
 
-Fine-tune BERT on a small sentiment analysis task using the
-[`keras_nlp.models`](https://keras.io/api/keras_nlp/models/) API:
+Fine-tune BERT on IMDb movie reviews:
 
 ```python
 import os
-os.environ["KERAS_BACKEND"] = "tensorflow"  # Or "jax" or "torch"!
+os.environ["KERAS_BACKEND"] = "jax"  # Or "tensorflow" or "torch"!
 
 import keras_nlp
 import tensorflow_datasets as tfds
@@ -96,8 +58,8 @@ imdb_train, imdb_test = tfds.load(
     batch_size=16,
 )
 # Load a BERT model.
-classifier = keras_nlp.models.BertClassifier.from_preset(
-    "bert_base_en_uncased", 
+classifier = keras_nlp.models.Classifier.from_preset(
+    "bert_base_en", 
     num_classes=2,
     activation="softmax",
 )
@@ -107,7 +69,35 @@ classifier.fit(imdb_train, validation_data=imdb_test)
 classifier.predict(["What an amazing movie!", "A total waste of my time."])
 ```
 
-For more in depth guides and examples, visit https://keras.io/keras_nlp/.
+Try it out [in a colab](https://colab.research.google.com/gist/mattdangerw/e457e42d5ea827110c8d5cb4eb9d9a07/kerasnlp-quickstart.ipynb).
+For more in depth guides and examples, visit
+[keras.io/keras_nlp](https://keras.io/keras_nlp/).
+
+## Installation
+
+To install the latest KerasNLP release with Keras 3, simply run:
+
+```
+pip install --upgrade keras-nlp
+```
+
+To install the latest nightly changes for both KerasNLP and Keras, you can use
+our nightly package.
+
+```
+pip install --upgrade keras-nlp-nightly
+```
+
+Note that currently, installing KerasNLP will always pull in TensorFlow for use
+of the `tf.data` API for preprocessing. Even when pre-processing with `tf.data`,
+training can still happen on any backend.
+
+Read [Getting started with Keras](https://keras.io/getting_started/) for more
+information on installing Keras 3 and compatibility with different frameworks.
+
+> [!IMPORTANT]
+> We recommend using KerasNLP with TensorFlow 2.16 or later, as TF 2.16 packages
+> Keras 3 by default.
 
 ## Configuring your backend
 
@@ -145,7 +135,8 @@ KerasNLP provides access to pre-trained models via the `keras_nlp.models` API.
 These pre-trained models are provided on an "as is" basis, without warranties
 or conditions of any kind. The following underlying models are provided by third
 parties, and subject to separate licenses:
-BART, DeBERTa, DistilBERT, GPT-2, OPT, RoBERTa, Whisper, and XLM-RoBERTa.
+BART, BLOOM, DeBERTa, DistilBERT, GPT-2, Llama, Mistral, OPT, RoBERTa, Whisper,
+and XLM-RoBERTa.
 
 ## Citing KerasNLP
 

api_gen.py

@@ -0,0 +1,86 @@
+# Copyright 2023 The KerasNLP Authors
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     https://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""Script to generate keras_nlp public API in `keras_nlp/api` directory.
+
+Usage:
+
+Run via `./shell/api_gen.sh`.
+It generates API and formats user and generated APIs.
+"""
+
+import os
+import shutil
+
+import namex
+
+package = "keras_nlp"
+
+
+def ignore_files(_, filenames):
+    return [f for f in filenames if f.endswith("_test.py")]
+
+
+def copy_source_to_build_directory(root_path):
+    # Copy sources (`keras_nlp/` directory and setup files) to build dir
+    build_dir = os.path.join(root_path, "tmp_build_dir")
+    if os.path.exists(build_dir):
+        shutil.rmtree(build_dir)
+    os.mkdir(build_dir)
+    shutil.copytree(
+        package, os.path.join(build_dir, package), ignore=ignore_files
+    )
+    return build_dir
+
+
+def export_version_string(api_init_fname):
+    with open(api_init_fname) as f:
+        contents = f.read()
+    with open(api_init_fname, "w") as f:
+        contents += "from keras_nlp.src.version_utils import __version__\n"
+        f.write(contents)
+
+
+def build():
+    # Backup the `keras_nlp/__init__.py` and restore it on error in api gen.
+    root_path = os.path.dirname(os.path.abspath(__file__))
+    code_api_dir = os.path.join(root_path, package, "api")
+    # Create temp build dir
+    build_dir = copy_source_to_build_directory(root_path)
+    build_api_dir = os.path.join(build_dir, package, "api")
+    build_init_fname = os.path.join(build_dir, package, "__init__.py")
+    build_api_init_fname = os.path.join(build_api_dir, "__init__.py")
+    try:
+        os.chdir(build_dir)
+        # Generates `keras_nlp/api` directory.
+        if os.path.exists(build_api_dir):
+            shutil.rmtree(build_api_dir)
+        if os.path.exists(build_init_fname):
+            os.remove(build_init_fname)
+        os.makedirs(build_api_dir)
+        namex.generate_api_files(
+            "keras_nlp", code_directory="src", target_directory="api"
+        )
+        # Add __version__ to keras package
+        export_version_string(build_api_init_fname)
+        # Copy back the keras_nlp/api and keras_nlp/__init__.py from build dir
+        if os.path.exists(code_api_dir):
+            shutil.rmtree(code_api_dir)
+        shutil.copytree(build_api_dir, code_api_dir)
+    finally:
+        # Clean up: remove the build directory (no longer needed)
+        shutil.rmtree(build_dir)
+
+
+if __name__ == "__main__":
+    build()

keras_nlp/conftest.py → conftest.py

@@ -15,10 +15,17 @@
 import os
 
 import pytest
-import tensorflow as tf
 
-from keras_nlp.backend import config as backend_config
-from keras_nlp.backend import keras
+try:
+    import tensorflow as tf
+except ImportError:
+    raise ImportError(
+        "To use `keras_nlp`, please install Tensorflow: `pip install tensorflow`. "
+        "The TensorFlow package is required for data preprocessing with any backend."
+    )
+
+from keras_nlp.src.backend import config as backend_config
+from keras_nlp.src.backend import keras
 
 
 def pytest_addoption(parser):

examples/utils/data_utils.py

@@ -15,7 +15,13 @@
 
 import os
 
-import tensorflow as tf
+try:
+    import tensorflow as tf
+except ImportError:
+    raise ImportError(
+        "To use `keras_nlp`, please install Tensorflow: `pip install tensorflow`. "
+        "The TensorFlow package is required for data preprocessing with any backend."
+    )
 from google import protobuf