
makeMoE
by AviSoori1x (personal account)
From scratch implementation of a sparse mixture of experts language model inspired by Andrej Karpathy's makemore :) (description from the project’s GitHub page)
Repository facts
- Stars
- 820
- Forks
- 96
- Open issues and pull requests
- 4
- Primary language
- Jupyter Notebook
- License
- MIT License (MIT)
- Owner
- AviSoori1x · Personal account
- Created
- Jan 22, 2024
- Last push
- Oct 30, 2024
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 3,017: learning-at-home/hivemind
Decentralized deep learning in PyTorch. Built to train models on thousands of volunteers across the world.
2,541 starsPythonMITLast push Jan 11, 2026
Rank 2,126: christianversloot/machine-learning-articles
🧠💬 Articles I wrote about machine learning, archived from MachineCurve.com.
3,699 starsNo license file detectedLast push Jun 28, 2024
Rank 768: bigscience-workshop/petals
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
10,639 starsPythonMITLast push Sep 7, 2024
Rank 1,851: algorithmicsuperintelligence/optillm
Optimizing inference proxy for LLMs
4,319 starsPythonApache-2.0Last push Oct 11, 2026
Rank 8,395: ymcui/Chinese-Mixtral
中文Mixtral混合专家大模型(Chinese Mixtral MoE LLMs)
613 starsPythonApache-2.0Last push Apr 19, 2026
Rank 9,362: Leeroo-AI/mergoo
A library for easily merging multiple LLM experts, and efficiently train the merged LLM.
515 starsPythonLGPL-3.0Last push Aug 26, 2024