MilesCranmer / pysr_scaling_laws
You should use PySR to find scaling laws. Here's an example.
☆33Updated last year
Alternatives and similar repositories for pysr_scaling_laws:
Users that are interested in pysr_scaling_laws are comparing it to the libraries listed below
- Fine-grained, dynamic control of neural network topology in JAX.☆21Updated last year
- Pytorch implementation of SuperPolyak subgradient method.☆43Updated 2 years ago
- ☆59Updated 3 years ago
- ☆15Updated 4 years ago
- Automated SMC with Probabilistic Program Proposals, for the Gen PPL.☆21Updated last year
- ☆24Updated last year
- ☆40Updated 3 months ago
- Turning SymPy expressions into JAX functions☆44Updated 3 years ago
- Bibtex for various Python science and machine learning software☆32Updated 2 years ago
- Your favourite classical machine learning algos on the GPU/TPU☆20Updated 2 months ago
- Supplementary code for the paper "Stationary Kernels and Gaussian Processes on Lie Groups and their Homogeneous Spaces"☆42Updated last year
- Dive into Jax, Flax, XLA and C++☆31Updated 4 years ago
- Source-to-Source Debuggable Derivatives in Pure Python☆15Updated last year
- Turn jitted jax functions back into python source code☆22Updated 2 months ago
- Code for paper https://arxiv.org/abs/2306.07961☆53Updated 8 months ago
- ☆13Updated 2 years ago
- ☆49Updated 2 years ago
- Exponential families for JAX☆63Updated this week
- Tools for JAX☆45Updated this week
- ☆28Updated 3 years ago
- "Parameter origami" -- folding and unfolding collections of parameters for optimization and sensitivity analysis.☆14Updated last year
- Visualize, create, and operate on pytrees in the most intuitive way possible.☆44Updated 2 months ago
- Wraps PyTorch code in a JIT-compatible way for JAX. Supports automatically defining gradients for reverse-mode AutoDiff.☆47Updated 2 weeks ago
- ☆18Updated 10 months ago
- Implementation of various equivariant models in JAX☆12Updated 11 months ago
- ☆21Updated last year
- In which I learn about score functions and how they can be used to generate data.☆16Updated 11 months ago
- Stencil computations in JAX☆70Updated last year
- Official code for paper: Conservative objective models are a special kind of contrastive divergence-based energy model☆14Updated last year
- Quantification of Uncertainty with Adversarial Models☆28Updated last year