GPTs trained with shakespeare dataset. Includes: small 10.8M GPT mimicking Andrej Karpathy's video lecture, Universal Transformer with Adaptive Computation Time
-
Updated
May 20, 2024 - Python
GPTs trained with shakespeare dataset. Includes: small 10.8M GPT mimicking Andrej Karpathy's video lecture, Universal Transformer with Adaptive Computation Time
TensorFlow 2.X reimplementation of PonderNet: Learning to Ponder, Andrea Banino, Jan Balaguer, Charles Blundell.
A PyTorch implementation of adaptive computation time RNNs that's clean, idiomatic, and extensible.
Unofficial Implementation of Universal Transformer https://arxiv.org/abs/1807.03819
Adaptive Computation Time in Chainer
Adaptive Computation Time (Graves, 2016, arXiv:1603.08983) wrapper for TensorFlow RNN cells.
first attempt at description2code from 2016
The implementation of Adaptive Computation function used in RNN "https://arxiv.org/pdf/1603.08983.pdf" and Universal Transformer Network "https://arxiv.org/pdf/1807.03819.pdf"
Alternative approach for Adaptive Computation Time in TensorFlow
Implementation of a Transformer that Ponders, using the scheme from the PonderNet paper
Add a description, image, and links to the adaptive-computation-time topic page so that developers can more easily learn about it.
To associate your repository with the adaptive-computation-time topic, visit your repo's landing page and select "manage topics."