Have finally upgraded to Pydantic 2! We know this could potentially be a big change – we held off for a while but now Pydantic 1 is EOL so we figured the time is right This is the ONLY change in this release, wanted to keep it really focused an minimize disruption
OPEN SOURCE
-
Daily Papers HackerNews Updated to Show Recent Papers First
By
–
updated daily papers hackernews to show more recent papers first with o1-mini
-
Open-Duck-Mini Robot Achieves First Steps with Neural Networks
By
–
Open-duck-mini proudly standing up for the first time!
— Thomas Wolf (@Thom_Wolf) 16 septembre 2024
Neural network powered 💥
Join the discussion if you're interested in cute-RL and sim-to-real transfer for open-source robots (you can help even without robotic hardware)👇 https://t.co/JINvI4it5MOpen-duck-mini proudly standing up for the first time! Neural network powered Join the discussion if you're interested in cute-RL and sim-to-real transfer for open-source robots (you can help even without robotic hardware)
-
Hugging Face Discord Launches New AutoTrain Support Channel
By
–
Hugging Face Discord just got a brand new AutoTrain Channel! Now, if you have any questions (small or big) regarding AutoTrain, you can directly ask in the channel and get (almost) instant help
-
Mini BDX: Open-Source AI Weekend Project Released
By
–
cute weekend project with @antoinepirrone (fully open-source https://
github.com/apirrone/mini_
BDX
… – with some rough edges atm – tutorial will come) -
Direct Preference Optimization Authors Discuss DPO Impact
By
–
Thrilled to have the authors of Direct Preference Optimization answering questions on their paper! DPO offers a simple alternative to RLHF and has been hugely impactful, including being used to train Llama 3! Talk to the authors @archit_sharma97 and team directly to learn more!
-
MIT Press Open Access Fund Supports Free Deep Learning Resources
By
–
The MIT Press Open Access fund has a donor providing 4X gift matching this month. If you donate here: https://
giving.mit.edu/search/node/36
64125
… it will help the press to develop and freely give away resources like http://
deeplearningbook.org -
Setting Up Gradio Demo on Hugging Face with o1-mini
By
–
setup a @Gradio demo for it on @huggingface, demo made by o1-mini https://t.co/VGjF6H4D53 pic.twitter.com/QiGp2oJxFo
— AK (@_akhaliq) 15 septembre 2024setup a @Gradio demo for it on @huggingface
, demo made by o1-mini -
VEnhancer v2: Enhanced Texture Details and Identity Preservation
By
–
VEnhancer update Release our version 2 checkpoint: venhancer_v2.pt . It is less creative, but is able to generate more texture details, and has better identity preservation, which is more suitable for enhancing videos with profiles. github: https://
github.com/Vchitect/VEnha
ncer
… -
LLaMa-Omni: Low-Latency Speech-to-Speech LLM Model Architecture
By
–
7). LLaMa-Omni – a model architecture for low-latency speech interaction with LLMs; it is based on Llama-3.1-8B-Instruct and can simultaneously generate both text and speech responses given speech instructions; responses can be generated with a response latency as low as 226ms…