pen.el
metaseq
pen.el | metaseq | |
---|---|---|
21 | 53 | |
465 | 6,389 | |
- | 0.4% | |
9.5 | 6.2 | |
over 1 year ago | 8 days ago | |
Emacs Lisp | Python | |
GNU General Public License v3.0 only | MIT License |
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.
pen.el
- Pen.el – Emacs-based operating system designed with holiness in mind
- I turned my AI project into Bible software after getting born-again
-
I wrote an Emacs package for ChatGPT
I'd like to also through https://github.com/semiosis/pen.el as an option. It integrates quite a few open source clients into emacs and can turn it into an "imaginary" editor of sorts
- pen.el: Pen.el stands for Prompt Engineering in emacs. Create, discover and use prompts to language models. Pen supports EleutherAI, Aleph-Alpha, HuggingFace
-
Created a Twitter bot to ask for prompts and input the prompts from the replies and tweet out the results… bad idea lol
Why not use emacs?
- 'pen.el': a package for prompt engineering in emacs. (It facilitates the creation, ongoing development, discovery and usage of prompts to a language model such as OpenAI's GPT-3 or EleutherAI's GPT-j.)
- Imaginary programming with GPT-3/Codex
- I say, if GPT3 is this phenomenal, can you imagine how jaw dropping GPT69 is gonna be?
-
Open call for an ELisp hacker to bring GitHub Copilot to Emacs (yes, really)
Sort of: Pen. https://github.com/semiosis/pen.el/
- Show HN: Pen.el (Working GPT-3/LM for Emacs with easy Docker install)
metaseq
-
Training great LLMs from ground zero in the wilderness as a startup
This is a super important issue that affects the pace and breadth of iteration of AI almost as much as the raw hardware improvements do. The blog is fun but somewhat shallow and not technical or very surprising if you’ve worked with clusters of GPUs in any capacity over the years. (I liked the perspective of a former googler, but I’m not sure why past colleagues would recommend Jax over pytorch for LLMs outside of Google.) I hope this newco eventually releases a more technical report about their training adventures, like the PDF file here: https://github.com/facebookresearch/metaseq/tree/main/projec...
- Chronicles of Opt Development
-
See the pitch memo that raised €105M for four-week-old startup Mistral
The number of people who can actually pre-train a true LLM is very small.
It remains a major feat with many tweaks and tricks. Case in point: the 114 pages of OPT175B logbook [1]
[1] https://github.com/facebookresearch/metaseq/blob/main/projec...
- Technologie: „Austro-ChatGPT“ – aber kein Geld zum Testen
- OPT (Open Pre-trained Transformers) is a family of NLP models trained on billions of tokens of text obtained from the internet
- Current state-of-the-art open source LLM
-
Elon Musk Buys Ten Thousand GPUs for Secretive AI Project
Reliability at scale: take a look at the OPT training log book for their 175B model run. It needed a lot of babysitting. In my experience, that scale of TPU training run requires a restart about once every 1-2 weeks—and they provide the middleware to monitor the health of the cluster and pick up on hardware failures.
-
Is AI Development more fun than Software Development?
I really appreciated this log of Facebook training a large language model of how troublesome AI development can be: https://github.com/facebookresearch/metaseq/tree/main/projects/OPT/chronicles
-
Visual ChatGPT
Stable Diffusion will run on any decent gaming GPU or a modern MacBook, meanwhile LLMs comparable to GPT-3/ChatGPT have had pretty insane memory requirements - e.g., <https://github.com/facebookresearch/metaseq/issues/146>
-
Ask HN: Is There On-Call in ML?
It seems so, check this log book from Meta: https://github.com/facebookresearch/metaseq/blob/main/projec...
What are some alternatives?
TabNine - AI Code Completions
stable-diffusion - A latent text-to-image diffusion model
check-if-email-exists - Check if an email address exists without sending any email, written in Rust. Comes with a ⚙️ HTTP backend.
nlp-resume-parser - NLP-powered, GPT-3 enabled Resume Parser from PDF to JSON.
vim-plugin - The Kite plugin for Vim.
GLM-130B - GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)
prompts - A free and open-source curation of prompts for OpenAI's GPT-3/Codex, EleutherAI's GPT-j, AlephAlpha's World Model and other language models.
gpt-2 - Code for the paper "Language Models are Unsupervised Multitask Learners"
asciinema - Terminal session recorder 📹
manim - Animation engine for explanatory math videos
copilot-cli - The AWS Copilot CLI is a tool for developers to build, release and operate production ready containerized applications on AWS App Runner or Amazon ECS on AWS Fargate.
cupscale - Image Upscaling GUI based on ESRGAN