tuning_playbook
awesome-chatgpt-prompts
tuning_playbook | awesome-chatgpt-prompts | |
---|---|---|
16 | 158 | |
25,209 | 104,393 | |
2.8% | - | |
4.7 | 7.0 | |
26 days ago | 9 days ago | |
HTML | ||
GNU General Public License v3.0 or later | Creative Commons Zero v1.0 Universal |
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
awesome-chatgpt-prompts
- Top ChatGPT prompts I could find with ranking system
- FLaNK Stack Weekly 12 February 2024
-
🌌 5 Open-Source GPT Wrappers to Boost Your AI Experience 🎁
Aside from the built-in prompts powered by awesome-chatgpt-prompts (Are you an ETH dev, a financial analyst, or a personal trainer today?), you can also create, share and debug your chat tools with prompt templates.
- Aprimorando as respostas do ChatGPT com prompts estratégicos
-
Ask HN: Daily practices for building AI/ML skills?
I've found the following resources helpful:
- 15 Rules For Crafting Effective GPT Chat Prompts (https://expandi.io/blog/chat-gpt-rules/)
- Awesome ChatGPT Prompts (https://github.com/f/awesome-chatgpt-prompts)
For more resources of like nature, you can search for "mega prompt".
-
Prompt writing communities
Someone assembled an adhoc page in Github that is amassing quite a large library of prompt ideas [Github]
-
Ask HN: Collection of best GPT-4 prompts?
I like to use PromptLayer for this. But you could easily set up a simple CRUD web app to track prompts/average completion token # length, different variations.
There is also awesome-chatgpt-prompts (https://github.com/f/awesome-chatgpt-prompts) which has some interesting ones. What are you looking for?
- Supercharge your writing with ChatGPT prompts
-
Introducing YourChat: A multi-platform LLM chat client that supports the APIs of text-generation-webui and llama.cpp.
* Built-In Prompts: Channel creativity using integrated prompts sourced from github.com/f/awesome-chatgpt-prompts.
-
Yet another ChatGPT generated workout... but modified.
So, I jumped into the ChatGPT fitness wagon to generate a New And Improved® workout that will have a mix of bodybuilding and calisthenics. I used a pre-made prompt to generate a PPL+FB and specified things like fitness leve, equipment, schedules, etc. in order to make if fit my current status. From there I made it fit some of my needs and chose some exercises that I wanted to do every day: wrist and core.
What are some alternatives?
dadaptation - D-Adaptation for SGD, Adam and AdaGrad
ChatGPT-pdf - A Chrome extension for downloading your ChatGPT history to PNG, PDF or a sharable link
arb - Arb has been merged into FLINT -- use https://github.com/flintlib/flint/ instead
gpt-prompts-cli - CLI for selecting or defining prompts to use with the ChatGPT chatbot, which retrieves the prompts from the awesome-chatgpt-prompts repository.
nn-zero-to-hero - Neural Networks: Zero to Hero
langchain - ⚡ Building applications with LLMs through composability ⚡ [Moved to: https://github.com/langchain-ai/langchain]
ML-Papers-Explained - Explanation to key concepts in ML
gpt_index - LlamaIndex (GPT Index) is a project that provides a central interface to connect your LLM's with external data. [Moved to: https://github.com/jerryjliu/llama_index]
Open-Assistant - OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
llm-workflow-engine - Power CLI and Workflow manager for LLMs (core package)
nanoGPT - The simplest, fastest repository for training/finetuning medium-sized GPTs.
chatgpt-google-extension - A browser extension that enhance search engines with ChatGPT