bigscience-workshop/petals
πΈ Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.
$ git clone https://github.com/young-geng/EasyLM.gitπΈ Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
γε€§θ―θ¨ζ¨‘εγδ½θ οΌθ΅΅ι«οΌζεζ― οΌε¨ζοΌε倩δΈοΌζη»§θ£
Build a modern LLM from scratch. Every line commented. Explained like we are five.
ExtremeBERT is a toolkit that accelerates the pretraining of customized language models on customized datasets, described in the paper βExtremeBERT: A Toolkit for Accelerating Pretraining of Customized BERTβ.
π« CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
An open-source, tool-augmented conversational language model from Fudan University
Data from GitHub Β· snapshot Sep 24, 2026