misko / human_descentLinks
β38Updated 8 months ago
Alternatives and similar repositories for human_descent
Users that are interested in human_descent are comparing it to the libraries listed below
Sorting:
- Implementation of Diffusion Transformer (DiT) in JAXβ292Updated last year
- π§± Modula software packageβ231Updated 2 weeks ago
- The boundary of neural network trainability is fractalβ215Updated last year
- β275Updated last year
- Getting crystal-like representations with harmonic lossβ194Updated 5 months ago
- Latent Program Network (from the "Searching Latent Program Spaces" paper)β93Updated 5 months ago
- β21Updated 4 months ago
- Bare-bones implementations of some generative models in Jax: diffusion, normalizing flows, consistency models, flow matching, (beta)-VAEsβ¦β133Updated last year
- Simple Transformer in Jaxβ140Updated last year
- Dion optimizer algorithmβ318Updated last week
- Brain-Inspired Modular Training (BIMT), a method for making neural networks more modular and interpretable.β172Updated 2 years ago
- β43Updated 3 weeks ago
- $100K or 100 Days: Trade-offs when Pre-Training with Academic Resourcesβ143Updated 3 months ago
- β180Updated 2 weeks ago
- β207Updated 9 months ago
- An implementation of PSGD Kron second-order optimizer for PyTorchβ96Updated last month
- β450Updated 10 months ago
- Minimal GPT (~350 lines with a simple task to test it)β62Updated 8 months ago
- CIFAR-10 speedruns: 94% in 2.6 seconds and 96% in 27 secondsβ288Updated last month
- supporting pytorch FSDP for optimizersβ84Updated 8 months ago
- Efficient optimizersβ259Updated last month
- WIPβ94Updated last year
- Minimal yet performant LLM examples in pure JAXβ150Updated last week
- β478Updated 3 weeks ago
- Automatic gradient descentβ210Updated 2 years ago
- Solve puzzles. Learn CUDA.β64Updated last year
- β27Updated last year
- Annotated version of the Mamba paperβ488Updated last year
- For optimization algorithm research and development.β532Updated this week
- Flow-matching algorithms in JAXβ104Updated last year