visual-chatgpt
metaseq
visual-chatgpt | metaseq | |
---|---|---|
50 | 53 | |
31,684 | 6,389 | |
- | 0.4% | |
8.9 | 6.2 | |
about 1 year ago | 7 days ago | |
Python | Python | |
MIT License | 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.
visual-chatgpt
-
Subtler Flex
For prompting, the GitHub repo I refer to the most is actually one from Microsoft: https://github.com/Microsoft/Visual-ChatGPT
-
OpenDILab Awesome Paper Collection: RL with Human Feedback (1)
Found relevant code at https://github.com/microsoft/visual-chatgpt + all code implementations here
-
[R] Low-code LLM: Visual Programming over LLMs - Yuzhe Cai et al , Microsoft Research Asia 2023
Github: https://github.com/microsoft/visual-chatgpt/tree/main/LowCodeLLM will soon be available!
-
It's been a week and there's already front ends for auto GPT. Is anyone else having a hard time keeping up with the take off? Are we seeing what exponential looks like?
It's not so much the size of the LLMs, it's what people are able to do with them in novel ways, e.g. https://github.com/microsoft/visual-chatgpt/tree/main/TaskMatrix.AI
- Taskmatrix.ai
- Introducing JARVIS : the new Microsoft's autonomous AI powered by HuggingGPT and ChatGPT.
-
How to make ChatGPT run tasks
There is a python library langchain, which microsoft used to give it access to image editing tools. You can write your own tools for it very easily, I've been having fun with it. I gave it internet search tools and it worked great at using current events in the response.
-
An AI researcher who has been warning about the technology for over 20 years says we should 'shut it all down,' and issue an 'indefinite and worldwide' ban.
Something like this: https://github.com/microsoft/visual-chatgpt/tree/main/TaskMatrix.AI could enable a far simpler AI to start making copies of itself.
-
HuggingGPT: Solving AI Tasks with ChatGPT and Its Friends in HuggingFace
Reminds me of VisualChatGPT (https://github.com/microsoft/visual-chatgpt), which also uses a LLM to decide what vision models to run.
-
ChatGPT is Inform8: interactive fiction with dual narration and action planes (both playable), dialogues, inner thoughts and the ability to argue about narration to change the course of action.
The best Microsoft API or overall API? It really depends what your goal is. https://github.com/huggingface is great if you want to dive right in, but https://github.com/microsoft/visual-chatgpt might be good as well (not easy to get to work locally).
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?
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
stable-diffusion - A latent text-to-image diffusion model
langchain - ⚡ Building applications with LLMs through composability ⚡ [Moved to: https://github.com/langchain-ai/langchain]
nlp-resume-parser - NLP-powered, GPT-3 enabled Resume Parser from PDF to JSON.
roomGPT - Upload a photo of your room to generate your dream room with AI.
GLM-130B - GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)
JARVIS - JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf
gpt-2 - Code for the paper "Language Models are Unsupervised Multitask Learners"
minimal-llama
manim - Animation engine for explanatory math videos
ControlNet - Let us control diffusion models!
cupscale - Image Upscaling GUI based on ESRGAN