Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, Llava, GLM4v, Ph…

《开源大模型食用指南》基于Linux环境快速部署开源大模型，更适合中国宝宝的部署教程

Yuan 2.0 Large Language Model

Mixture-of-Experts (MoE) Language Model

Example models using DeepSpeed

SwissArmyTransformer is a flexible and powerful library to develop your own Transformer variants.

《Machine Learning Systems: Design and Implementation》- Chinese Version

LiBai(李白): A Toolbox for Large-Scale Distributed Parallel Training

Ongoing research training transformer models at scale

Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch

High-Resolution Image Synthesis with Latent Diffusion Models

Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

CodeBERT

Pre-Training with Whole Word Masking for Chinese BERT（中文BERT-wwm系列模型）

Crime assistant including crime type prediction and crime consult service based on nlp methods and crime kg,罪名法务智能项目,内容包括856项罪名知识图谱, 基于280万罪名训练库的罪名预测,基于20W法务问答对的13类问题分类与法律资讯问答功能.

Introduction to CPM

🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.

组内追更订会相关论文

Source code and dataset for ACL 2019 paper "ERNIE: Enhanced Language Representation with Informative Entities"

DyNet: The Dynamic Neural Network Toolkit