Re-implementation of 'Grokking: Generalization beyond overfitting on small algorithmic datasets'
☆38Dec 4, 2021Updated 4 years ago
Alternatives and similar repositories for grokking
Users that are interested in grokking are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- The original weights of some Caffe models, ported to PyTorch.☆11Jan 18, 2022Updated 4 years ago
- ☆10Sep 13, 2021Updated 4 years ago
- Visual search interface☆11Nov 30, 2021Updated 4 years ago
- Contrastive Language-Audio Pretraining☆15May 18, 2021Updated 5 years ago
- Self-Similarity Priors: Neural Collages as Differentiable Fractal Representations☆30Nov 26, 2022Updated 3 years ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch☆89Dec 3, 2021Updated 4 years ago
- ☆11Apr 14, 2022Updated 4 years ago
- ESGD-M is a stochastic non-convex second order optimizer, suitable for training deep learning models, for PyTorch.☆57Sep 18, 2022Updated 3 years ago
- Mechanistic Interpretability for Transformer Models☆53Jun 1, 2022Updated 4 years ago
- This repository hosts code for converting the original MLP Mixer models (JAX) to TensorFlow.☆15Sep 29, 2021Updated 4 years ago
- ☆13Sep 17, 2021Updated 4 years ago
- Finetune the 1.4B latent diffusion text2img-large checkpoint from CompVis using deepspeed. (work-in-progress)☆36Apr 17, 2022Updated 4 years ago
- Official code for "Accelerating Feedforward Computation via Parallel Nonlinear Equation Solving", ICML 2021☆30Sep 25, 2021Updated 4 years ago
- DALLE-tools provided useful dataset utilities to improve you workflow with WebDatasets.☆14Mar 9, 2022Updated 4 years ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- ☆19Aug 19, 2021Updated 4 years ago
- Training simple models to predict CLIP image embeddings from text embeddings, and vice versa.☆60Mar 31, 2022Updated 4 years ago
- ☆19Oct 3, 2022Updated 3 years ago
- Official code for On Path Integration of Grid Cells: Group Representation and Isotropic Scaling (NeurIPS 2021)☆54Nov 10, 2021Updated 4 years ago
- A better PyTorch implementation of image local attention which reduces the GPU memory by an order of magnitude.☆141Dec 21, 2021Updated 4 years ago
- Doing style transfer with linguistic features using OpenAI's CLIP.☆14May 4, 2021Updated 5 years ago
- Directed masked autoencoders☆15Mar 25, 2026Updated 2 months ago
- Texture mapping with variational auto-encoders☆40Oct 1, 2021Updated 4 years ago
- SNAIL Attention Block for Keras.☆17Mar 30, 2020Updated 6 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Official repository for the paper: "Trees with Attention for Set Prediction Tasks" (ICML21)☆10Jan 19, 2022Updated 4 years ago
- VQGAN+CLIP with some additional tuning. For notebooks and the command line.☆50Aug 20, 2021Updated 4 years ago
- CLOOB training (JAX) and inference (JAX and PyTorch)☆74May 16, 2022Updated 4 years ago
- A basic implementation of the paper Eigengame : PCA as a Nash Equilibrium☆21Jun 7, 2021Updated 5 years ago
- A python library for highly configurable transformers - easing model architecture search and experimentation.☆48Nov 30, 2021Updated 4 years ago
- Repository for the "Gotta Go Fast When Generating Data with Score-Based Models" paper☆105Nov 20, 2021Updated 4 years ago
- Repo for storing the files I use to make animations with big-sleep, deep-daze, and VQGAN + CLIP.☆16Sep 14, 2021Updated 4 years ago
- Variational autoencoder for Lego minifig faces☆16May 22, 2023Updated 3 years ago
- Unofficial Alias-Free GAN implementation. Based on rosinality's version with expanded training and inference options.☆76Aug 3, 2023Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆93Nov 26, 2021Updated 4 years ago
- Script and models for clustering LAION-400m CLIP embeddings.☆26Jan 10, 2022Updated 4 years ago
- ☆27Oct 8, 2021Updated 4 years ago
- ☆96Oct 27, 2022Updated 3 years ago
- A convolution-free, transformer-only version of the CycleGAN framework☆33Feb 12, 2022Updated 4 years ago
- ☆27Mar 13, 2021Updated 5 years ago
- Digital paint mixing program based on the Kubelka-Munk equations. Implementation of : T. Lindemeier, J. M. Gülzow, and O. Deussen. 2018…☆14Sep 10, 2020Updated 5 years ago