tuning_playbook
ChatGPT
| tuning_playbook | ChatGPT | |
|---|---|---|
| 16 | 52 | |
| 25,545 | 51,326 | |
| 3.1% | - | |
| 4.6 | 5.5 | |
| 4 days ago | 12 days ago | |
| Rust | ||
| GNU General Public License v3.0 or later | GNU Affero General Public License v3.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
tuning_playbook
-
When Random Numbers Are Too Random: Low Discrepancy Sequences
These are also called quasirandom numbers. Despite games, another use case is for hyperparameter search for neural networks.
https://github.com/google-research/tuning_playbook?tab=readm...
-
Hyperparameter Optimization for LLMs via Scaling Laws
[2] https://github.com/google-research/tuning_playbook
-
Beyond Automatic Differentiation
Batch size can be used for regularisation, but using it for that will limit training performance. From the Google Research Tuning Playbook:
> The batch size governs the training speed and shouldn't be used to directly tune the validation set performance. Often, the ideal batch size will be the largest batch size supported by the available hardware.
> […]
> As long as all hyperparameters are well-tuned (especially the learning rate and regularization hyperparameters) and the number of training steps is sufficient, the same final performance should be attainable using any batch size (see Shallue et al. 2018).
https://github.com/google-research/tuning_playbook#choosing-...
The ideal case is full-batch with tuneable regularisation, just the hardware gets expensive.
-
Modeling methodology
Regarding tuning params, this is an excellent read: https://github.com/google-research/tuning_playbook
- About the hardware
- I asked an AI to create an Asmongold story and then had another AI generate voice. There it is dude
-
Trending ML repos of the week 📈
3️⃣ google-research/tuning_playbook
- AI全靠偷欧美开源的
- Deep learning tuning playbook
ChatGPT
- Widen ChatGPT Screen
- Noi: an AI-enhanced, customizable browser
-
What AI assistants are already bundled for Linux?
> I wouldn't hold my breath waiting for a native Linux AI-assisted assistant.
On Mac when I press Command + Space, it brings up Spotlight search
That can't easily be added to be the equivalent of some kind of LLM prompt on GNOME/KDE/XFCE?
I don't quite know what you'd ask it/do with it that would be of much value? Seems like a quicker way/a wrapper around either asking an LLM questions via CLI or basically Electron wrapping HTML (like this https://github.com/lencx/ChatGPT)?
-
The Top 10 GitHub Repositories Making Waves 🌊📊
Github | Website
- Is there a website where I can ser all the new and latest ChatGPT plugins anf their features ?
- Has anyone tried these desktop versions of ChatGPT?
-
Is there a better option than ShareGPT for getting an entire conversation with formatting?
I am using lencx/ChatGPT app since its launch and I am quite happy with it. it have option to export chat in multiple types... I really like Prompt database feature. Love it.
-
make text (chatgpt) wider, now is too narrow
i tried to find the workaround on google but only found the solution using bookmark technique. here is the link. https://github.com/lencx/ChatGPT/issues/430 (mattinordstrom answer). the thing is the solution is using bookmark and javascript. i read the code line and guess the class and property being used but still not working. thank you so much
-
How to search all the previous chats (at least by title)?
Is there any way I can search the previous chats? I'm using a desktop app (this one: https://github.com/lencx/ChatGPT) and it does not seem to have this feature as well.
-
Are there any github repos that allow you to use the ChatGPT UI as an API?
Also, I keep warning people to not put your API keys into other people's software. This is what you get: https://github.com/lencx/ChatGPT/discussions/849
What are some alternatives?
dadaptation - D-Adaptation for SGD, Adam and AdaGrad
askai - Command Line Interface for OpenAi ChatGPT
arb - Arb has been merged into FLINT -- use https://github.com/flintlib/flint/ instead
BetterChatGPT - An amazing UI for OpenAI's ChatGPT (Website + Windows + MacOS + Linux)
nn-zero-to-hero - Neural Networks: Zero to Hero
nanoGPT - The simplest, fastest repository for training/finetuning medium-sized GPTs.
ML-Papers-Explained - Explanation to key concepts in ML
chatgpt-raycast - ChatGPT raycast extension
Open-Assistant - OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
PyChatGPT - ⚡️ Python client for the unofficial ChatGPT API with auto token regeneration, conversation tracking, proxy support and more.
chat-ai-desktop - Unofficial ChatGPT desktop app for Mac & Windows menubar using Tauri & Rust