Spiffy AI

[Yoshitomo Matsubara @yoshitomo_cs]

Released torchdistill v1.1.0 last night!

⚗️ Key updates ⚗️
- @PyTorch 2.2.1 support
- 3 new KD methods
- Custom low-level loss support

https://t.co/IXWsYr2nsx

For the new KD methods (SRD w/ @Miles12Roy), we reproduced ImageNet results (2 wins, 1 lose)
https://t.co/zjDmK5RAgU

[Yoshitomo Matsubara @yoshitomo_cs]

I’m happy to share that I’m starting a new position as Founding Research Engineer @SpiffyAI !

This is a totally new adventure for me. I am very excited to join such an amazing team and work together on challenging problems!

[Sameer Singh @sameer_]

LLMs have problems that are difficult to identify and explain. To understand them better, we need to study the relationship between LLMs and their pre-training data, and with the OLMo release, @allen_ai helps make this possible!

https://t.co/KYX8Ahzo3U

[Iz Beltagy @i_beltagy]

OLMo-7b is finally out 🎉, and we are releasing everything; weights, intermediate checkpoints, training code and logs, training data and toolkit, evaluation and adaptation code and data.

Most of it has been released, and the rest is coming soon. OLMo-65b and Adapted OLMo-7b are training, and we plan extensions to future modalities. Check the report for details https://t.co/LEH7gBZUTd

Thanks to all of @allen_ai, especially those who took the project from zero-to-one: @mechanicaldirk, Pete Walsh, @akshitab93, Rodney Kinney, @oyvindtafjord, @AnanyaHarsh, @hamishivi, @IanMagnusson, @yizhongwyz, Kyle Richardson, @LukeZettlemoyer, @soldni, @nlpnoah, @HannaHajishirzi