AI Disruption

AI Disruption

Share this post

AI Disruption
AI Disruption
30 Latest AI Open Source Projects of the Week(2024.12.2-2024.12.6)
Copy link
Facebook
Email
Notes
More

30 Latest AI Open Source Projects of the Week(2024.12.2-2024.12.6)

Explore 30 exciting AI open-source projects this week (2024.12.2-2024.12.6), featuring cutting-edge models like INTELLECT-1, GLM-Edge, and HunyuanVideo!

Meng Li's avatar
Meng Li
Dec 09, 2024
∙ Paid
5

Share this post

AI Disruption
AI Disruption
30 Latest AI Open Source Projects of the Week(2024.12.2-2024.12.6)
Copy link
Facebook
Email
Notes
More
3
Share

I’m sharing some interesting AI open-source models and frameworks for this week (2024.12.2-2024.12.6).
There are a total of 30 AI open-source projects.

Project: INTELLECT-1

Intellect 1 training visual

INTELLECT-1 is a decentralized, community-trained language model with 10B parameters, focusing on training from scratch using 1 trillion English text and code tokens.

The model is trained across 14 globally distributed nodes, aiming for high performance and fault-tolerant dynamic scaling.

Prime Intellect: World's First Decentralized Large Model, Fully Open-Sourced

Prime Intellect: World's First Decentralized Large Model, Fully Open-Sourced

Meng Li
·
December 2, 2024
Read full story

https://huggingface.co/PrimeIntellect/INTELLECT-1


Project: GLM-Edge

GLM-Edge is a dialogue generation model developed by the Knowledge Engineering and Data Mining team at Tsinghua University.

This project is based on the Transformer architecture, specializing in text generation tasks, particularly dialogue generation.

The model supports Chinese and performs exceptionally well in edge computing environments, making it ideal for applications requiring efficient dialogue generation.

https://github.com/THUDM/GLM-Edge


Project: minRLHF

minRLHF: Reinforcement Learning from Human Feedback from Scratch cover image

minRLHF is a minimal implementation of RLHF (Reinforcement Learning with Human Feedback) based on Karpathy's minGPT library.

This project aims to provide a small, clear, interpretable, and educational GPT implementation.

minRLHF extends minGPT to demonstrate how to implement complex language model training and inference within a small-scale codebase.

https://github.com/ttumiel/minRLHF


Project: GitDigest

GitDigest is a web interface that converts GitHub repositories into text summaries optimized for prompts in large language models (LLMs).

Users can simply paste a GitHub repository URL to get instant analysis results.

The project offers intelligent formatting to optimize LLM prompts and provides insights such as file and directory structure, token counts, statistics, and repository summaries.

https://github.com/cyclotruc/gitingest


Project: Report

The Report project provides an alternative to Jupyter Notebooks for data analysis and visualization by generating Python files.

It emphasizes code readability and auditability, with outputs presented as static HTML pages for easy sharing and presentation of analysis results.

https://github.com/yobibyte/report


Project: Rig

Rig logo

Rig is a Rust library for building scalable, modular, and ergonomic LLM-powered applications.

It offers comprehensive support for LLM completion and embedding workflows, integrating LLM providers and vector stores through a simple yet powerful abstraction layer.

Rig is designed to integrate LLMs into applications with minimal boilerplate code.

https://github.com/0xPlaygrounds/rig


This post is for paid subscribers

Already a paid subscriber? Sign in
© 2025 Meng Li
Privacy ∙ Terms ∙ Collection notice
Start writingGet the app
Substack is the home for great culture

Share

Copy link
Facebook
Email
Notes
More