metaseq
ChatGPT.el
metaseq | ChatGPT.el | |
---|---|---|
53 | 14 | |
6,389 | 396 | |
0.4% | - | |
6.2 | 6.9 | |
10 days ago | 6 months ago | |
Python | Emacs Lisp | |
MIT License | GNU General Public License v3.0 only |
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.
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...
ChatGPT.el
- Emacs-copilot: Large language model code completion for Emacs
-
JetBrains IDE update previews “deeply integrated” AI Assistant
I presume it's this? https://github.com/joshcho/ChatGPT.el
-
What's everyone using for grammar checks?
Chatgpt, use one of the many emacs chatgpt packages, send the content to chatgpt with something as simple as: fix grammar, example https://github.com/d1egoaz/c3po.el#correct-grammar-and-show-detailed-changes-in-a-diff-buffer https://github.com/joshcho/ChatGPT.el etc
- Suggest a gpt plugin for me
- A ChatGPT Emacs Shell
- ChatGPT in Emacs
- Show HN: Neovim Plugin for ChatGPT
-
Show HN: ChatGPT-arcana.el, ChatGPT in your Emacs
There's also https://github.com/joshcho/ChatGPT.el but it hasn't been updated yet to use the API that came out yesterday.
- I Made a ChatGPT Client For Emacs - AND SO CAN YOU!
- ChatGPT.el
What are some alternatives?
stable-diffusion - A latent text-to-image diffusion model
gpt4all - gpt4all: run open-source LLMs anywhere
nlp-resume-parser - NLP-powered, GPT-3 enabled Resume Parser from PDF to JSON.
codeium.vim - Free, ultrafast Copilot alternative for Vim and Neovim
GLM-130B - GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)
gptel - A simple LLM client for Emacs
gpt-2 - Code for the paper "Language Models are Unsupervised Multitask Learners"
lsp-ltex - lsp-mode ❤️ LTEX
manim - Animation engine for explanatory math videos
CodeGPT.nvim - CodeGPT is a plugin for neovim that provides commands to interact with ChatGPT.
cupscale - Image Upscaling GUI based on ESRGAN
flycheck-vale - Flycheck integration for the vale natural language linter