google-deepmind / dksLinks
Multi-framework implementation of Deep Kernel Shaping and Tailored Activation Transformations, which are methods that modify neural network models (and their initializations) to make them easier to train.
☆74Updated 3 months ago
Alternatives and similar repositories for dks
Users that are interested in dks are comparing it to the libraries listed below
Sorting:
- Pytorch implementation of preconditioned stochastic gradient descent (Kron and affine preconditioner, low-rank approximation precondition…☆188Updated 2 weeks ago
- Meta-learning inductive biases in the form of useful conserved quantities.☆37Updated 2 years ago
- Official repository for the paper "Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks"☆59Updated 3 years ago
- ☆115Updated last month
- Open source code for EigenGame.☆33Updated 2 years ago
- ☆58Updated last year
- Automatically take good care of your preemptible TPUs☆37Updated 2 years ago
- Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX☆88Updated last year
- Implementation of Gradient Agreement Filtering, from Chaubard et al. of Stanford, but for single machine microbatches, in Pytorch☆25Updated 9 months ago
- Implementation of GateLoop Transformer in Pytorch and Jax☆90Updated last year
- minGPT in JAX☆48Updated 3 years ago
- Latent Diffusion Language Models☆69Updated 2 years ago
- Demo of the unit_scaling library, showing how a model can be easily adapted to train in FP8.