feat: complete blog post on nested tokenization#58
Conversation
Summary of ChangesHello @KarelZe, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request completes and publishes two distinct blog posts by updating their metadata. The primary post, as indicated by the title, focuses on 'nested tokenization', while a second post discusses 'faithful synthetic data'. Both are transitioned from draft status to public, making them accessible to readers. Highlights
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request marks two blog posts, 'How Faithful is Your Synthetic Data?' and 'Nested Tokenization for Larger Context in Large Images', as ready for publication by changing the draft status to false. However, a review of the content reveals that both posts are incomplete and contain numerous issues such as TODO comments, personal notes, typos, and unfinished sentences. Publishing them in their current state would be premature. I recommend reverting these changes and completing the posts before merging. Additionally, there is a potentially redundant index.md.draft file for the 'Nested Tokenization' post, which should be clarified.
| description: My thoughts on the paper "How Faithful is Your Synthetic Data?". | ||
| DisableComments: false | ||
| draft: true | ||
| draft: false |
There was a problem hiding this comment.
This post is being marked for publication, but it appears to be incomplete. It contains several TODO comments which indicate that work is still pending. Publishing the article in this state is likely not intended.
Here are the locations of the TODOs:
- Line 129:
TODO: add d3.js plot... - Line 185:
TODO: Simplify into simple train-val loop... - Line 405:
TODO: simplify. - Line 518:
TODO: its unclear to me, what the k-nn is used for. - Line 534:
TODO: translate + make a svg - Line 544:
TODO: translate + make a svg
Please complete these sections and remove the TODO comments before setting draft: false.
| draft: false | |
| draft: true |
| description: My thoughts on the paper "Nested Tokenization for Larger Context in Large Images". | ||
| disableComments: false | ||
| draft: true | ||
| draft: false |
There was a problem hiding this comment.
This post is being marked for publication, but it seems to be an unfinished draft. It contains several personal comments, typos, and an incomplete sentence that should be addressed before publishing.
Specifically:
- Personal notes/comments that look like reminders for the author on lines 34, 35, 38, 39, and 47. These should be removed or integrated into the main text.
- Typos:
- Line 22: "Ressources" should be "Resources".
- Line 36: "down-sights" should be "downsides".
- Line 37: "Mare practically" should be "More practically".
- Incomplete sentence on line 40, which ends with "while".
Please finish editing this post before marking it as ready for publication.
| draft: false | |
| draft: true |
| categories: [ai] | ||
| disableComments: false | ||
| draft: true | ||
| draft: false |
There was a problem hiding this comment.
This file, which appears to be a draft version of nested-tokenization/index.md, is also being marked for publication. It contains the same issues as the main markdown file, such as personal comments and incomplete content.
Furthermore, having both index.md and index.md.draft for the same post is confusing. It's unclear if this file is intended for publication or if it's a backup that should be removed.
Please clarify the purpose of this file. If it's not meant to be published, it should be removed or kept as a draft. If it is, it needs to be completed first.
draft: true
1 participant
No description provided.