Pinned
OpenGPT-2: We Replicated GPT-2 Because You Can Too! 1.5B Model Weights Released.
Blogpost: medium.com/@vanya_cohen/o…
Colab: colab.research.google.com/drive/1esbpDOo…
Aaron Gokaslan
3,882 posts
Aaron Gokaslan
@SkyLi0n
Creator of OpenWebText. @PyTorch/@pybind11 maintainer @Mozilla Rise25. Prev. @MBZUAI IFM Pretraining Infra Lead @Cornell (PhD) @FacebookAI and @BrownUniversity
Joined September 2015
- Just opened a PR yesterday that will reduce the binary size PyTorch by 40% by adding 1 flag to NVCC With ~50M monthly of downloads of Pytorch, this one change will reduce global internet traffic by ~20PB. High impact changes like this is why I love OSS.
- Replying to @Miles_BrundageThis is apparently in their style guide. It's a very anachronistic way of spelling it, but it was valid once upon a time.
- Replying to @unusual_whalesThis isn't just Canad's oldest retailer, this is the oldest company in North America, and one of the oldest in the world.
- Can GANs outperform diffusion models in 2024? Yes! #2200: The GAN is dead; long live the GAN! A Modern GAN Baseline! Come join me if you're attending NeurIPS 2024. Thursday evening poster session 4:30-7:30 . #NeurIPSConference with @zonkedNGray @volokuleshov @jtompkin
- "First Order Motion Model for Image Animation" by Siarohin et al. transfers surprisingly well to animated characters.
00:00 - Want to try the new Latent Diffusion, but don't want to pay for Google Colab Pro? @multimodalart @RiversHaveWings and I have optimized the inference of the model so it can run in the free version of Google Colab:
- Replying to @karpathyReminds me of how Trinity tests polluted all future steel for scientific experiments:
- Replying to @soumithchintalapybind11 powers @llvmorg, @matplotlib, @SciPy_team, @PyTorch, @TensorFlow, and many other projects. We average 5 million+ git clones a month, and that is not including pypi.org downloads or binaries that ship the code.
- Replying to @SkyLi0n
- I am on the job market for industry and academic roles. My research focuses identifying, designing, and building efficient, scalable, sustainable, and affordable abstractions and infrastructure for generative modeling research. I also minor law, and do AI policy work.
- Replying to @Shalev_lif and @delipraoBut it does use diffusion lol
