bigscience-workshop/petals
▲ +16 ★ this week
🌸 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.git▲ +16 ★ this week
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
▲ +7 ★ this week
《大语言模型》作者:赵鑫,李军毅,周昆,唐天一,文继荣
▲ +6 ★ this week
Build a modern LLM from scratch. Every line commented. Explained like we are five.
[ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
ExtremeBERT is a toolkit that accelerates the pretraining of customized language models on customized datasets, described in the paper “ExtremeBERT: A Toolkit for Accelerating Pretraining of Customized BERT”.
Run Effective Large Batch Contrastive Learning Beyond GPU/TPU Memory Constraint
Data from GitHub · snapshot Nov 16, 2026