By
–
Also, thanks to @isaac_flath, the gallery is now an official FastHTML project! Now available at the URL below: https://t.co/T4Ro4KIK0H
— Jeremy Howard (@jeremyphoward) 20 août 2024
Also, thanks to @isaac_flath
, the gallery is now an official FastHTML project! Now available at the URL below:
By
–
Back to work after a much needed family break! Who’s ready to have fun for the last six months of 2024? What should we focus on @huggingface
?
By
–
.@huggingface passed 5 million users pic.twitter.com/TBjSy8ZvZ3
— AK (@_akhaliq) 19 août 2024
.
@huggingface passed 5 million users
By
–
We passed 5 million users.
— Hugging Face (@huggingface) 19 août 2024
🥳That's 5 million of you who have signed up on the Hub 🚀 thank you for contributing to the ecosystem and making open Machine Learning happen!
We're just getting started 🤗 pic.twitter.com/8Ls3kZXdTg
We passed 5 million users. That's 5 million of you who have signed up on the Hub thank you for contributing to the ecosystem and making open Machine Learning happen! We're just getting started
By
–
#opensource wins, purchase a card or system at http://
tenstorrent.com
By
–
Thank you @RepZoeLofgren for speaking out against the anti-open source, anti-innovation bill SB-1047. She is the ranking member of the House Science, Space and Technology Committee. Her staff concludes: "the problematic core concerns remain: there is little evidentiary basis
By
–
New Update, T2V results from CogVideoX + VEnhancerhttps://t.co/vTwpiJXvPw
— AK (@_akhaliq) 19 août 2024
Support enhancement for abitrary long videos (by spliting the videos into muliple chunks with overlaps); Fewer sampling steps (15) are enabled without obvious quality loss by setting –solver_mode 'fast'… pic.twitter.com/k32HTS3g0j
New Update, T2V results from CogVideoX + VEnhancer https://
github.com/Vchitect/VEnha
ncer?tab=readme-ov-file#-news
… Support enhancement for abitrary long videos (by spliting the videos into muliple chunks with overlaps); Fewer sampling steps (15) are enabled without obvious quality loss by setting –solver_mode 'fast'
By
–
The vast majority of Internet servers use Linux
By
–
Salesforce presents xGen-MM (BLIP-3) A Family of Open Large Multimodal Models discuss: https://
huggingface.co/papers/2408.08
872
… This report introduces xGen-MM (also known as BLIP-3), a framework for developing Large Multimodal Models (LMMs). The framework comprises meticulously curated
By
–
It depends. If you have TPUs, Jax. If you have GPUs, PyTorch. It also depends on who your community is, and whether you need to distribute models or not. For simple ML, either is fine and then it comes down to popularity within your circle.