Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!

AgentScope: Agent-Oriented Programming for Building LLM Applications

Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习

📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程

Language Technology Platform

An Open-Source Package for Knowledge Embedding (KE)

🔍大模型应用开发实战一：RAG 技术全栈指南，在线阅读地址：https://datawhalechina.github.io/all-in-rag/

The official implementation of [CVPR2022] Decoupled Knowledge Distillation https://arxiv.org/abs/2203.08679 and [ICCV2023] DOT: A Distillation-Oriented Trainer https://openaccess.thecvf.com/content…

RAG for Local LLM, chat with PDF/doc/txt files, ChatPDF. 纯原生实现RAG功能，基于本地LLM、embedding模型、reranker模型实现，支持GraphRAG，无须安装任何第三方agent库。

PromptKG Family: a Gallery of Prompt Learning & KG-related research works, toolkits, and paper-list.

Multi-task learning using uncertainty to weigh losses for scene geometry and semantics, Auxiliary Tasks in Multi-task Learning

Code and resources on scalable and efficient Graph Neural Networks (TNNLS 2023)

[NeurIPS'24] Knowledge Graph Fine-Tuning using LLMs

Semantically Structured Sentence Embeddings

The offical implementation of [NeurIPS2024] Wasserstein Distance Rivals Kullback-Leibler Divergence for Knowledge Distillation https://arxiv.org/abs/2412.08139

The official implementation of the CVPR'2022 paper Hyperspherical Consistency Regularization.

Feature Fusion for Online Mutual Knowledge Distillation Code

PyTorch implementation of Lessons on Parameter Sharing across Layers in Transformers

Complementary Relation Contrastive Distillation

PyTorch Implementation of Attention Prompt Tuning: Parameter-Efficient Adaptation of Pre-Trained Models for Action Recognition

[NAACL2024 main] Code Repository for our paper - The Integration of Semantic and Structural Knowledge in Knowledge Graph Entity Typing