1a3orn / very-simple-moeLinks
Extremely simple MoE implementation, mostly based off Switch Transformer
☆12Updated last year
Alternatives and similar repositories for very-simple-moe
Users that are interested in very-simple-moe are comparing it to the libraries listed below
Sorting:
- Code for "Counterfactual Token Generation in Large Language Models", Arxiv 2024.☆31Updated last year
- Minimum Description Length probing for neural network representations☆20Updated 10 months ago
- Engineering the state of RNN language models (Mamba, RWKV, etc.)☆32Updated last year
- PyTorch implementation for "Long Horizon Temperature Scaling", ICML 2023☆20Updated 2 years ago
- Simple repository for training small reasoning models☆47Updated 10 months ago
- 📰 Computing the information content of trained neural networks☆22Updated 4 years ago
- Google Research☆46Updated 3 years ago
- Your favourite classical machine learning algos on the GPU/TPU☆20Updated 11 months ago
- Embedding Recycling for Language models☆38Updated 2 years ago
- Implementation of the Kalman Filtering Attention proposed in "Kalman Filtering Attention for User Behavior Modeling in CTR Prediction"☆59Updated 2 years ago
- Aioli: A unified optimization framework for language model data mixing☆31Updated 10 months ago
- Unofficially Implements https://arxiv.org/abs/2112.05682 to get Linear Memory Cost on Attention for PyTorch☆12Updated 3 years ago
- JAX/Flax implementation of the Hyena Hierarchy☆34Updated 2 years ago
- Training and evaluation code for the paper "Headless Language Models: Learning without Predicting with Contrastive Weight Tying" (https:/…☆28Updated last year
- Understanding how features learned by neural networks evolve throughout training☆40Updated last year
- Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount …☆53Updated 2 years ago
- Experiments on GPT-3's ability to fit numerical models in-context.☆14Updated 3 years ago
- Implementation of GateLoop Transformer in Pytorch and Jax☆91Updated last year
- A place to store reusable transformer components of my own creation or found on the interwebs☆63Updated this week
- ☆56Updated last year
- Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification☆11Updated 2 years ago
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆59Updated 2 years ago
- Code for papers Linear Algebra with Transformers (TMLR) and What is my Math Transformer Doing? (AI for Maths Workshop, Neurips 2022)☆76Updated last year
- Implementation of Gradient Agreement Filtering, from Chaubard et al. of Stanford, but for single machine microbatches, in Pytorch☆25Updated 10 months ago
- Triton Implementation of HyperAttention Algorithm☆48Updated 2 years ago
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆103Updated 11 months ago
- [COLM 2024] Early Weight Averaging meets High Learning Rates for LLM Pre-training☆18Updated last year
- Official implementation of "BERTs are Generative In-Context Learners"☆32Updated 8 months ago
- QLoRA for Masked Language Modeling☆22Updated 2 years ago
- A collection of lightweight interpretability scripts to understand how LLMs think☆68Updated 2 weeks ago