From 70c3db9ea2e909e83968171006a72b3a7a40b0a2 Mon Sep 17 00:00:00 2001 From: Ryan Mullins Date: Tue, 9 Jul 2024 16:11:35 +0000 Subject: [PATCH] Fixing second-person lint errors --- site/en/gemma/docs/lit_gemma.ipynb | 43 ++++++++++++++++++------------ 1 file changed, 26 insertions(+), 17 deletions(-) diff --git a/site/en/gemma/docs/lit_gemma.ipynb b/site/en/gemma/docs/lit_gemma.ipynb index 1d79c35d0..3b7418878 100644 --- a/site/en/gemma/docs/lit_gemma.ipynb +++ b/site/en/gemma/docs/lit_gemma.ipynb @@ -125,9 +125,10 @@ "source": [ "## Install LIT and Keras NLP\n", "\n", - "Here, we use the KerasNLP implementation of Gemma (more on how to configure this\n", - "below). You will need a recent version of `keras` (3.0+) `keras-nlp`\n", - "(0.12+) and `lit-nlp` (1.2+), and a Kaggle account to download the base model." + "This notebook uses the KerasNLP implementation of Gemma (more on how to \n", + "configure this below). You will need a recent version of `keras` (3.0+) \n", + "`keras-nlp` (0.12+) and `lit-nlp` (1.2+), and a Kaggle account to download the \n", + "base model." ] }, { @@ -153,10 +154,10 @@ "source": [ "### Kaggle Access\n", "\n", - "KerasNLP stores their pre-trained model weights on Kaggle. We use the\n", - "[`kagglehub` package](https://github.com/Kaggle/kagglehub#authenticate) to\n", - "autheticate with this service. Be sure to also accept the license agreement for\n", - "[Gemma](https://www.kaggle.com/models/keras/gemma) from your Kaggle account.\n", + "KerasNLP stores their pre-trained model weights on Kaggle. The\n", + "[`kagglehub` package](https://github.com/Kaggle/kagglehub#authenticate) is used\n", + "to autheticate with this service. Be sure to also accept the license agreement \n", + "for [Gemma](https://www.kaggle.com/models/keras/gemma) from your Kaggle account.\n", "\n", "See the Appendix at the end for more information on how to set up a Kaggle\n", "account." @@ -190,9 +191,14 @@ "id": "v12sUSdiNPje" }, "source": [ - "LIT provides a function, `make_notebook_widget()` for configuring our prompt debugging tools in a notebook context. The first two arguments define the `datasets` and `models`, respectively, and are required. The remaining parameters allow you to choose \n", + "LIT provides a function, `make_notebook_widget()` for configuring our prompt \n", + "debugging tools in a notebook context. \n", "\n", - "We provide a dataset of sample prompts that support the case studies later in this document. If you" + "LIT provides a dataset of sample prompts that accompany the tutorial linked \n", + "later in this document.\n", + "\n", + "See the comments below for configuring the widget to use different models and/or\n", + "datasets." ] }, { @@ -210,9 +216,9 @@ "#\n", "# * `datasets_config`: A list of strings containing the dataset names and\n", "# paths to load from, as \"dataset:path\", where path can be a URL or a\n", - "# local file path. Here, we use a special value, `sample_prompts`, to load\n", - "# the example prompts provided in the LIT distribution; no other special\n", - "# values are supported.\n", + "# local file path. The example below uses a special value,\n", + "# `sample_prompts`, to load the example prompts provided in the LIT\n", + "# distribution; no other special values are supported.\n", "# * `models_config`: A list of strings containing the model names and paths to\n", "# load from, as \"model:path\", where path can be a URL, a local file path,\n", "# or the name of a preset for the configured deep learning framework.\n", @@ -284,9 +290,9 @@ "\n", "[Salience methods][salience-explorable] allow you to inspect which parts of an \n", "input are important to the model for different parts of its generated output. \n", - "LIT's [Sequence Salience module][lit-seq-sal] extends these methods so that we\n", - "can explain importance at multiple levels of granularity: from tokens to words\n", - "to sentences and beyond.\n", + "LIT's [Sequence Salience module][lit-seq-sal] extends these methods to explain \n", + "the importance of sequences at multiple levels of granularity: from tokens to \n", + "words to sentences and beyond.\n", "\n", "You can use LIT in the cell above to play around with the Sequence Salience \n", "module on your own. For a more guided learning experience, you can follow long \n", @@ -312,9 +318,12 @@ "source": [ "# Appendix: Accessing Gemma on Kaggle Hub\n", "\n", - "We use the KerasNLP implementation of Gemma in this document. KerasNLP stores their pre-trained model weights on Kaggle, and Gemma requires authentication and license acknowledgement to access those weights.\n", + "This notebook uses the KerasNLP implementation of Gemma in this document. \n", + "KerasNLP stores their pre-trained model weights on Kaggle, and Gemma requires \n", + "authentication and license acknowledgement to access those weights.\n", "\n", - "The following instruction walk you through how to set up a Kaggle account and authenticate with Kaggle using the `kagglehub` package.\n", + "The following instruction walk you through how to set up a Kaggle account and \n", + "authenticate with Kaggle using the `kagglehub` package.\n", "\n", "1. Create a Kaggle account if you don't have one\n", " * Go to: https://www.kaggle.com/account/login?phase=startRegisterTab\n",