Li-Lai

streamv2v

Official Pytorch implementation of StreamV2V.

sharik

Sharik is an open-source, cross-platform solution for sharing files via Wi-Fi or Mobile Hotspot

stb

stb single-file public domain libraries for C/C++

Real3DPortrait

Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis; ICLR 2024 Spotlight; Official code

AniPortrait

AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation

OpenRLHF

An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & Mixtral)

MAP-NEO

fastllm

纯c++的全平台llm加速库，支持python调用，chatglm-6B级模型单卡可达10000+token / s，支持glm, llama, moss基座，手机端流畅运行

fish-speech

Brand new TTS solution

lightning-whisper-mlx

An extremely fast implementation of whisper optimized for Apple Silicon using MLX.

DouyinLiveRecorder

可循环值守和多人录制的直播录制软件，支持抖音、TikTok、快手、虎牙、斗鱼、B站、小红书、pandatv、afreecatv、flextv、popkontv、twitcasting、winktv、百度、微博、酷狗、花椒、流星等平台直播录制，抓取多平台直播源地址

Awesome-LLMs-Datasets

Summarize existing representative LLMs text datasets.

ragflow

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

SCB-dataset

Student Classroom Behavior dataset

xtuner

An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)

Steel-LLM

Train a Chinese LLM From 0 by Personal

kungfu

Kungfu Trader

data-science-competition

该仓库用于记录作者本人参加的各大数据科学竞赛的获奖方案源码以及一些新比赛的原创baseline. 主要涵盖：kaggle, 阿里天池，华为云大赛校园赛，百度aistudio，和鲸社区，datafountain等

baby-llama2-chinese

用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.

labelU

Data annotation toolbox supports image, audio and video data.

Chinese-CLIP

Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.

CLIP-Chinese

中文CLIP预训练模型

Open-GroundingDino

This is the third party implementation of the paper Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection.

OLMo

Modeling, training, eval, and inference code for OLMo

TinyRAG

TinyRAG

MFTCoder

High Accuracy and efficiency multi-task fine-tuning framework for Code LLMs. This work has been accepted by KDD 2024.

MNBVC

MNBVC(Massive Never-ending BT Vast Chinese corpus)超大规模中文语料集。对标chatGPT训练的40T数据。MNBVC数据集不但包括主流文化，也包括各个小众文化甚至火星文的数据。MNBVC数据集包括新闻、作文、小说、书籍、杂志、论文、台词、帖子、wiki、古诗、歌词、商品介绍、笑话、糗事、聊天记录等一切形式的纯文本中文数据。

ChatGPTBook

《ChatGPT原理与实战：大型语言模型的算法、技术和私有化》

bytepiece

更纯粹、更高压缩率的Tokenizer

frigate

NVR with realtime local object detection for IP cameras