Making large AI models cheaper, faster and more accessible

The official Meta Llama 3 GitHub site

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

A repository sharing the literatures about long-context large language models, including the methodologies and the evaluation benchmarks

Code and Data for "Long-context LLMs Struggle with Long In-context Learning" [TMLR2025]

ChatLaw：A Powerful LLM Tailored for Chinese Legal. 中文法律大模型

LongLLaMA is a large language model capable of handling long contexts. It is based on OpenLLaMA and fine-tuned with the Focused Transformer (FoT) method.

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

allreduce benchmark using deepspeed

Ongoing research training transformer models at scale

⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platforms⚡

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

Inference code for Llama models

Code for the paper "Evaluating Large Language Models Trained on Code"

An annotated implementation of the Transformer paper.

🦜🔗 The platform for reliable agents.

放一些有趣的code

http request/response parser for c