TensorOps organization, TransformerX Python library. Transformer-based models' building blocks for Tensorflow, Pytorch, and Jax. Discord: https://xitter.cf/t.co/fFIGkciBwW
Joined August 2022
- Tweets14
- Following8
- Followers9
- Likes113
Tensorops retweeted
How can Hamiltonian mechanics apply to generative modeling and Markov chain Monte Carlo? @soranghadri presents a thoughtful deep dive on a fascinating topic. towardsdatascience.com/from-…
Tensorops retweeted
📌 Hi all! Here's my brief intro to Hamiltonian Monte Carlo and H-mechanics. It breaks down the math (fully explained) and includes bits of visualizations. #mcmc #hamiltonianMonteCarlo #generativeAI
How can Hamiltonian mechanics apply to generative modeling and Markov chain Monte Carlo? @soranghadri presents a thoughtful deep dive on a fascinating topic. towardsdatascience.com/from-…
Tensorops retweeted
Finally got around to deploying the first version of the TorchEBM docs! It’s a little library I’ve been tinkering with for energy-based models in PyTorch. Still very early stages—think rough draft vibes—but it’s open-source and meant for research tinkering. [1/n]
Tensorops retweeted
For the past month, I have been developing TorchEBM, a library for modeling and training energy-based models. I'm actively developing it. Any suggestions, insights, or contributions are welcome.
github.com/soran-ghaderi/tor…
🎉 Exciting news! The TransformerX library has just received a major update, bringing enhanced performance and new features to the table. 🚀 Stay tuned for the stable release in the coming days.💬 #TransformerX #NLP #research #Transformers #DeepLearning
Tensorops retweeted
Catch up with the recent history of Transformers research — @soranghadri's overview is comprehensive and accessible; it's a powerful resource to bookmark for future reference. buff.ly/43N2Opt
Tensorops retweeted
. @soranghadri explains transformer architecture through underlying math, Python code implementation, and visualization of different layers. buff.ly/3RJRiEk
Tensorops retweeted
Scaled dot-product attention is a type of #attention_mechanism where the dot-products of tensors are scaled down by √dk which normalizes the q.k variance to 1.
Check out towardsdatascience.com/trans… for more. #Transformers
Also in the #TransformerX library: github.com/tensorops/Transfo…
Tensorops retweeted
Transformers in Action: Attention Is All You Need by @soranghadri buff.ly/3RJRiEk
TransformerX is now available on PyPi 🎉
pip install transformerx
GitHub: github.com/tensorops/Transfo…
TransformerX is a Python library that comes with a range of building blocks you need to implement transformer-based models. It helps researchers implement their models with ease.
We have made the TransformerX Python library public on GitHub. The library will be available on PyPI soon.
github.com/tensorops/Transfo…