Stars
MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents [EMNLP 2024]
Arena-Hard-Auto: An automatic LLM benchmark.
A generative speech model for daily dialogue.
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
[ECCV 2024] ShareGPT4V: Improving Large Multi-modal Models with Better Captions
A modular graph-based Retrieval-Augmented Generation (RAG) system
The official implementation of Self-Play Preference Optimization (SPPO)
[ACL 2024] IEPile: A Large-Scale Information Extraction Corpus
SimPO: Simple Preference Optimization with a Reference-Free Reward
Official style files for papers submitted to venues of the Association for Computational Linguistics
Data and Code for EMNLP 2023 paper "QTSumm: Query-Focused Summarization over Tabular Data"
Code and data for the NAACL 2024 paper "Embrace Divergence for Richer Insights: A Multi-document Summarization Benchmark and a Case Study on Summarizing Diverse Information from News Articles"
中文羊驼大模型三期项目 (Chinese Llama-3 LLMs) developed from Meta Llama 3
mPLUG-Owl: The Powerful Multi-modal Large Language Model Family
Label Studio is a multi-type data labeling and annotation tool with standardized output format
LabelImg is now part of the Label Studio community. The popular image annotation tool created by Tzutalin is no longer actively being developed, but you can check out Label Studio, the open source …
Official inference library for Mistral models
Mixture-of-Experts for Large Vision-Language Models
[ECCV 2024] OMG: Occlusion-friendly Personalized Multi-concept Generation In Diffusion Models
Awesome-LLM-RAG: a curated list of advanced retrieval augmented generation (RAG) in Large Language Models
An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & Mixtral)
Retrieval Augmented Generation (RAG) chatbot powered by Weaviate
Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines
Build ChatGPT over your data, all with natural language
实现了Baichuan-Chat微调,Lora、QLora等各种微调方式,一键运行。