capybara-brain346/moe-router
A small Mixture-of-Experts (MoE) Transformer trained from scratch to learn how sparse expert models work and to study their performance, routing behavior, and efficiency under realistic conditions.
Stars
2
Forks
—
Language
Python
License
MIT
Category
Last pushed
Nov 17, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/capybara-brain346/moe-router"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
UKPLab/gpl
Powerful unsupervised domain adaptation method for dense retrieval. Requires only unlabeled...
galilai-group/stable-pretraining
Reliable, minimal and scalable library for pretraining foundation and world models
svdrecbd/mhc-mlx
MLX + Metal implementation of mHC: Manifold-Constrained Hyper-Connections by DeepSeek-AI.
CognitiveAISystems/MAPF-GPT
[AAAI-2025] This repository contains MAPF-GPT, a deep learning-based model for solving MAPF...
larslorch/avici
Amortized Inference for Causal Structure Learning, NeurIPS 2022