diff --git a/README.md b/README.md index 4ca23f1c..616e0268 100644 --- a/README.md +++ b/README.md @@ -240,6 +240,18 @@ Character Model：Paimon; Pose Model：Hold Sign

+ + + + + + + + +
+

+Style Model：ShinYunBok

+ ## BibTeX ``` @article{guo2023animatediff, @@ -256,4 +268,4 @@ Pose Model：Hold Sig **Bo Dai**: [daibo@pjlab.org.cn](mailto:daibo@pjlab.org.cn) ## Acknowledgements -Codebase built upon [Tune-a-Video](https://github.com/showlab/Tune-A-Video). \ No newline at end of file +Codebase built upon [Tune-a-Video](https://github.com/showlab/Tune-A-Video). diff --git a/__assets__/animations/model_09/01.gif b/__assets__/animations/model_09/01.gif new file mode 100644 index 00000000..1622749e Binary files /dev/null and b/__assets__/animations/model_09/01.gif differ diff --git a/__assets__/animations/model_09/02.gif b/__assets__/animations/model_09/02.gif new file mode 100644 index 00000000..819c0ba4 Binary files /dev/null and b/__assets__/animations/model_09/02.gif differ diff --git a/__assets__/animations/model_09/03.gif b/__assets__/animations/model_09/03.gif new file mode 100644 index 00000000..02e7cecf Binary files /dev/null and b/__assets__/animations/model_09/03.gif differ diff --git a/__assets__/animations/model_09/04.gif b/__assets__/animations/model_09/04.gif new file mode 100644 index 00000000..16f3cb44 Binary files /dev/null and b/__assets__/animations/model_09/04.gif differ diff --git a/site/en/gemma/docs/keras_inference.ipynb b/site/en/gemma/docs/keras_inference.ipynb new file mode 100644 index 00000000..a7d6bc17 --- /dev/null +++ b/site/en/gemma/docs/keras_inference.ipynb @@ -0,0 +1,623 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": { + "id": "Tce3stUlHN0L" + }, + "source": [ + "##### Copyright 2024 Google LLC." + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "cellView": "form", + "id": "tuOe1ymfHZPu" + }, + "outputs": [], + "source": [ + "#@title Licensed under the Apache License, Version 2.0 (the \"License\");\n", + "# you may not use this file except in compliance with the License.\n", + "# You may obtain a copy of the License at\n", + "#\n", + "# https://www.apache.org/licenses/LICENSE-2.0\n", + "#\n", + "# Unless required by applicable law or agreed to in writing, software\n", + "# distributed under the License is distributed on an \"AS IS\" BASIS,\n", + "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n", + "# See the License for the specific language governing permissions and\n", + "# limitations under the License." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "4qxv4Sn9b8CE" + }, + "source": [ + "\n", + " \n", + " \n", + " \n", + " \n", + "
\n", + " View on ai.google.dev\n", + " \n", + " Run in Google Colab\n", + " \n", + " Open in Vertex AI\n", + " \n", + " View source on GitHub\n", + "
" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "PXNm5_p_oxMF" + }, + "source": [ + "# Get started with Gemma using KerasNLP\n", + "\n", + "This tutorial shows you how to get started with Gemma using [KerasNLP](https://keras.io/keras_nlp/). Gemma is a family of lightweight, state-of-the art open models built from the same research and technology used to create the Gemini models. KerasNLP is a collection of natural language processing (NLP) models implemented in [Keras](https://keras.io/) and runnable on JAX, PyTorch, and TensorFlow.\n", + "\n", + "In this tutorial, you'll use Gemma to generate text responses to several prompts. If you're new to Keras, you might want to read [Getting started with Keras](https://keras.io/getting_started/) before you begin, but you don't have to. You'll learn more about Keras as you work through this tutorial." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "mERVCCsGUPIJ" + }, + "source": [ + "## Setup" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "QQ6W7NzRe1VM" + }, + "source": [ + "### Gemma setup\n", + "\n", + "To complete this tutorial, you'll first need to complete the setup instructions at [Gemma setup](https://ai.google.dev/gemma/docs/setup). The Gemma setup instructions show you how to do the following:\n", + "\n", + "* Get access to Gemma on kaggle.com.\n", + "* Select a Colab runtime with sufficient resources to run\n", + " the Gemma 2B model.\n", + "* Generate and configure a Kaggle username and API key.\n", + "\n", + "After you've completed the Gemma setup, move on to the next section, where you'll set environment variables for your Colab environment." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "_gN-IVRC3dQe" + }, + "source": [ + "### Set environment variables\n", + "\n", + "Set environment variables for `KAGGLE_USERNAME` and `KAGGLE_KEY`." + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "metadata": { + "id": "DrBoa_Urw9Vx" + }, + "outputs": [], + "source": [ + "import os\n", + "from google.colab import userdata\n", + "\n", + "# Note: `userdata.get` is a Colab API. If you're not using Colab, set the env\n", + "# vars as appropriate for your system.\n", + "os.environ[\"KAGGLE_USERNAME\"] = userdata.get('KAGGLE_USERNAME')\n", + "os.environ[\"KAGGLE_KEY\"] = userdata.get('KAGGLE_KEY')" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "z9oy3QUmXtSd" + }, + "source": [ + "### Install dependencies\n", + "\n", + "Install Keras and KerasNLP." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "UcGLzDeQ8NwN" + }, + "outputs": [], + "source": [ + "# Install Keras 3 last. See https://keras.io/getting_started/ for more details.\n", + "!pip install -q -U keras-nlp\n", + "!pip install -q -U \"keras>=3\"" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "Pm5cVOFt5YvZ" + }, + "source": [ + "### Select a backend\n", + "\n", + "Keras is a high-level, multi-framework deep learning API designed for simplicity and ease of use. [Keras 3](https://keras.io/keras_3) lets you choose the backend: TensorFlow, JAX, or PyTorch. All three will work for this tutorial." + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": { + "id": "7rS7ryTs5wjf" + }, + "outputs": [], + "source": [ + "import os\n", + "\n", + "os.environ[\"KERAS_BACKEND\"] = \"jax\" # Or \"tensorflow\" or \"torch\".\n", + "os.environ[\"XLA_PYTHON_CLIENT_MEM_FRACTION\"] = \"0.9\"" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "599765c72722" + }, + "source": [ + "### Import packages\n", + "\n", + "Import Keras and KerasNLP." + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": { + "id": "f2fa267d75bc" + }, + "outputs": [], + "source": [ + "import keras\n", + "import keras_nlp" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "ZsxDCbLN555T" + }, + "source": [ + "## Create a model\n", + "\n", + "KerasNLP provides implementations of many popular [model architectures](https://keras.io/api/keras_nlp/models/). In this tutorial, you'll create a model using `GemmaCausalLM`, an end-to-end Gemma model for causal language modeling. A causal language model predicts the next token based on previous tokens.\n", + "\n", + "Create the model using the `from_preset` method:" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "yygIK9DEIldp" + }, + "outputs": [], + "source": [ + "gemma_lm = keras_nlp.models.GemmaCausalLM.from_preset(\"gemma2_2b_en\")\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "XrAWvsU6pI0E" + }, + "source": [ + "The `GemmaCausalLM.from_preset()` function instantiates the model from a preset architecture and weights. In the code above, the string `\"gemma2_2b_en\"` specifies the preset the Gemma 2 2B model with 2 billion parameters. Gemma models with [7B, 9B, and 27B parameters](/gemma/docs/get_started#models-list) are also available. You can find the code strings for Gemma models in their **Model Variation** listings on [Kaggle](https://www.kaggle.com/models/google/gemma).\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "Ij73k0PfUhjE" + }, + "source": [ + "Note: To run the larger models in Colab, you need access to the premium GPUs available in paid plans. Alternatively, you can perform inferences using Kaggle notebooks or Google Cloud projects.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "E-cSEjULUhST" + }, + "source": [ + "Use `summary` to get more info about the model:" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": { + "id": "e5nEbTdApL7W", + "outputId": "c7f65192-7fbf-489d-8b1d-a24b1e83cce2", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 408 + } + }, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "\u001b[1mPreprocessor: \"gemma_causal_lm_preprocessor\"\u001b[0m\n" + ], + "text/html": [ + "
Preprocessor: \"gemma_causal_lm_preprocessor\"\n",
+              "
\n" + ] + }, + "metadata": {} + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n", + "┃\u001b[1m \u001b[0m\u001b[1mTokenizer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Vocab #\u001b[0m\u001b[1m \u001b[0m┃\n", + "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n", + "│ gemma_tokenizer (\u001b[38;5;33mGemmaTokenizer\u001b[0m) │ \u001b[38;5;34m256,000\u001b[0m │\n", + "└────────────────────────────────────────────────────┴─────────────────────────────────────────────────────┘\n" + ], + "text/html": [ + "
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n",
+              "┃ Tokenizer (type)                                   ┃                                             Vocab # ┃\n",
+              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n",
+              "│ gemma_tokenizer (GemmaTokenizer)                   │                                             256,000 │\n",
+              "└────────────────────────────────────────────────────┴─────────────────────────────────────────────────────┘\n",
+              "
\n" + ] + }, + "metadata": {} + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "\u001b[1mModel: \"gemma_causal_lm\"\u001b[0m\n" + ], + "text/html": [ + "
Model: \"gemma_causal_lm\"\n",
+              "
\n" + ] + }, + "metadata": {} + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n", + "┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mConnected to \u001b[0m\u001b[1m \u001b[0m┃\n", + "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n", + "│ padding_mask (\u001b[38;5;33mInputLayer\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ - │\n", + "├───────────────────────────────┼───────────────────────────┼─────────────────┼────────────────────────────┤\n", + "│ token_ids (\u001b[38;5;33mInputLayer\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ - │\n", + "├───────────────────────────────┼───────────────────────────┼─────────────────┼────────────────────────────┤\n", + "│ gemma_backbone │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m2304\u001b[0m) │ \u001b[38;5;34m2,614,341,888\u001b[0m │ padding_mask[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m], │\n", + "│ (\u001b[38;5;33mGemmaBackbone\u001b[0m) │ │ │ token_ids[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n", + "├───────────────────────────────┼───────────────────────────┼─────────────────┼────────────────────────────┤\n", + "│ token_embedding │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256000\u001b[0m) │ \u001b[38;5;34m589,824,000\u001b[0m │ gemma_backbone[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n", + "│ (\u001b[38;5;33mReversibleEmbedding\u001b[0m) │ │ │ │\n", + "└───────────────────────────────┴───────────────────────────┴─────────────────┴────────────────────────────┘\n" + ], + "text/html": [ + "
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓\n",
+              "┃ Layer (type)                  ┃ Output Shape              ┃         Param # ┃ Connected to               ┃\n",
+              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━┩\n",
+              "│ padding_mask (InputLayer)     │ (None, None)              │               0 │ -                          │\n",
+              "├───────────────────────────────┼───────────────────────────┼─────────────────┼────────────────────────────┤\n",
+              "│ token_ids (InputLayer)        │ (None, None)              │               0 │ -                          │\n",
+              "├───────────────────────────────┼───────────────────────────┼─────────────────┼────────────────────────────┤\n",
+              "│ gemma_backbone                │ (None, None, 2304)        │   2,614,341,888 │ padding_mask[0][0],        │\n",
+              "│ (GemmaBackbone)               │                           │                 │ token_ids[0][0]            │\n",
+              "├───────────────────────────────┼───────────────────────────┼─────────────────┼────────────────────────────┤\n",
+              "│ token_embedding               │ (None, None, 256000)      │     589,824,000 │ gemma_backbone[0][0]       │\n",
+              "│ (ReversibleEmbedding)         │                           │                 │                            │\n",
+              "└───────────────────────────────┴───────────────────────────┴─────────────────┴────────────────────────────┘\n",
+              "
\n" + ] + }, + "metadata": {} + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m2,614,341,888\u001b[0m (9.74 GB)\n" + ], + "text/html": [ + "
 Total params: 2,614,341,888 (9.74 GB)\n",
+              "
\n" + ] + }, + "metadata": {} + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m2,614,341,888\u001b[0m (9.74 GB)\n" + ], + "text/html": [ + "
 Trainable params: 2,614,341,888 (9.74 GB)\n",
+              "
\n" + ] + }, + "metadata": {} + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n" + ], + "text/html": [ + "
 Non-trainable params: 0 (0.00 B)\n",
+              "
\n" + ] + }, + "metadata": {} + } + ], + "source": [ + "gemma_lm.summary()" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "81KHdRYOrWYm" + }, + "source": [ + "As you can see from the summary, the model has 2.6 billion trainable parameters.\n", + "\n", + "Note: For purposes of naming the model (\"2B\"), the embedding layer is not counted against the number of parameters." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "FOBW7piN5-sl" + }, + "source": [ + "## Generate text\n", + "\n", + "Now it's time to generate some text! The model has a `generate` method that generates text based on a prompt. The optional `max_length` argument specifies the maximum length of the generated sequence.\n", + "\n", + "Try it out with the prompt `\"what is keras in 3 bullet points?\"`." + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": { + "id": "aae5GHrdpj2_", + "outputId": "362ab0d4-80d2-4a65-eb91-f28d055511ec", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 53 + } + }, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "'what is keras in 3 bullet points?\\n\\n[Answer 1]\\n\\nKeras is a high-level neural networks API, written in Python and capable of running on top of TensorFlow, CNTK, Theano, or PlaidML. It is designed to be user-friendly and easy to extend.\\n\\n'" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "string" + } + }, + "metadata": {}, + "execution_count": 9 + } + ], + "source": [ + "gemma_lm.generate(\"what is keras in 3 bullet points?\", max_length=64)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "qH0eFH_DvYwM" + }, + "source": [ + "Try calling `generate` again with a different prompt." + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": { + "id": "VEyTnnNGvgGG", + "outputId": "a6193127-2a71-481d-8521-d3c21f7dd148", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 53 + } + }, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "'The universe is a vast and mysterious place, filled with countless stars, planets, and galaxies. But what if there was a way to see the universe in a whole new way? What if we could see the universe as it was when it was first created? What if we could see the universe as it is now'" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "string" + } + }, + "metadata": {}, + "execution_count": 16 + } + ], + "source": [ + "gemma_lm.generate(\"The universe is\", max_length=64)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "vVlCnY7Gvm7U" + }, + "source": [ + "If you're running on JAX or TensorFlow backends, you'll notice that the second `generate` call returns nearly instantly. This is because each call to `generate` for a given batch size and `max_length` is compiled with XLA. The first run is expensive, but subsequent runs are much faster." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "mw5XkiHU11Ft" + }, + "source": [ + "You can also provide batched prompts using a list as input:" + ] + }, + { + "cell_type": "code", + "execution_count": 17, + "metadata": { + "id": "xV6vs8_C2BGt", + "outputId": "e972806a-1983-408b-bf0e-43f36c95c14a", + "colab": { + "base_uri": "https://localhost:8080/" + } + }, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "['what is keras in 3 bullet points?\\n\\n[Answer 1]\\n\\nKeras is a high-level neural networks API, written in Python and capable of running on top of TensorFlow, CNTK, Theano, or PlaidML. It is designed to be user-friendly and easy to extend.\\n\\n',\n", + " 'The universe is a vast and mysterious place, filled with countless stars, planets, and galaxies. But what if there was a way to see the universe in a whole new way? What if we could see the universe as it was when it was first created? What if we could see the universe as it is now']" + ] + }, + "metadata": {}, + "execution_count": 17 + } + ], + "source": [ + "gemma_lm.generate(\n", + " [\"what is keras in 3 bullet points?\",\n", + " \"The universe is\"],\n", + " max_length=64)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "MaVWoSpo3XyY" + }, + "source": [ + "### Optional: Try a different sampler\n", + "\n", + "You can control the generation strategy for `GemmaCausalLM` by setting the `sampler` argument on `compile()`. By default, [`\"greedy\"`](https://keras.io/api/keras_nlp/samplers/greedy_sampler/#greedysampler-class) sampling will be used.\n", + "\n", + "As an experiment, try setting a [`\"top_k\"`](https://keras.io/api/keras_nlp/samplers/top_k_sampler/) strategy:" + ] + }, + { + "cell_type": "code", + "execution_count": 20, + "metadata": { + "id": "mx55VQpN4DAK", + "outputId": "29c7a52c-6575-4487-cf83-66c8eb7d8772", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 53 + } + }, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "'The universe is a big place, and there are so many things we do not know or understand about it.\\n\\nBut we can learn a lot about our world by studying what is known to us.\\n\\nFor example, if you look at the moon, it has many features that can be seen from the surface.'" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "string" + } + }, + "metadata": {}, + "execution_count": 20 + } + ], + "source": [ + "gemma_lm.compile(sampler=\"top_k\")\n", + "gemma_lm.generate(\"The universe is\", max_length=64)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "-okKgK4LfO0f" + }, + "source": [ + "While the default greedy algorithm always picks the token with the largest probability, the top-K algorithm randomly picks the next token from the tokens of top K probability.\n", + "\n", + "You don't have to specify a sampler, and you can ignore the last code snippet if it's not helpful to your use case. If you'd like learn more about the available samplers, see [Samplers](https://keras.io/api/keras_nlp/samplers/)." + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "jBrbTYasoo-J" + }, + "source": [ + "## What's next\n", + "\n", + "In this tutorial, you learned how to generate text using KerasNLP and Gemma. Here are a few suggestions for what to learn next:\n", + "\n", + "* Learn how to [finetune a Gemma model](https://ai.google.dev/gemma/docs/lora_tuning).\n", + "* Learn how to perform [distributed fine-tuning and inference on a Gemma model](https://ai.google.dev/gemma/docs/distributed_tuning).\n", + "* Learn about [Gemma integration with Vertex AI](https://ai.google.dev/gemma/docs/integrations/vertex)\n", + "* Learn how to [use Gemma models with Vertex AI](https://cloud.google.com/vertex-ai/docs/generative-ai/open-models/use-gemma)." + ] + } + ], + "metadata": { + "accelerator": "GPU", + "colab": { + "provenance": [], + "gpuType": "T4" + }, + "google": { + "image_path": "/site-assets/images/marketing/gemma.png", + "keywords": [ + "examples", + "gemma", + "python", + "quickstart", + "text" + ] + }, + "kernelspec": { + "display_name": "Python 3", + "name": "python3" + } + }, + "nbformat": 4, + "nbformat_minor": 0 +} \ No newline at end of file