Ma-Dan

llama2.c

Inference Llama 2 in one file of pure C

llama.cpp

Port of Facebook's LLaMA model in C/C++

agibot_x1_hardware

The hardware design for AgiBot X1.

agibot_x1_infer

The inference module for AgiBot X1.

agibot_x1_train

The reinforcement learning training code for AgiBot X1.

embodied-generalist

[ICML 2024] Official code repository for 3D embodied generalist agent LEO

FireRedASR

Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR benchmarks, while also offering outstanding singing lyrics recognition capability.

FlappyBird

Less than 100 Kilobytes. Works for Android 5.1 and above

Hands-on-RL

https://hrl.boyuai.com/

hil-serl

humanoid-gym

Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer https://arxiv.org/abs/2404.05695

icefall

jitsi-meet

Jitsi Meet - Secure, Simple and Scalable Video Conferences that you use as a standalone app or embed in your web application.

k2

FSA/FST algorithms, differentiable, with PyTorch compatibility.

ktransformers

A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations

llm-export

llm-export can export llm model to onnx.

MinerU

A one-stop, open-source, high-quality data extraction tool, supports PDF/webpage/e-book extraction.一站式开源高质量数据提取工具，支持PDF/网页/多格式电子书提取。

mnn-llm

llm deploy project based mnn.

MoneyPrinterTurbo

利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.

RoboWaiter

大模型具身智能比赛-机器人控制端

sherpa-ncnn

Real-time speech recognition using next-gen Kaldi with ncnn

simpleRL-reason

This is a replicate of DeepSeek-R1-Zero and DeepSeek-R1 training on small models with limited data

tensor.h

creating a tiny tensor library in raw C

Thinking-Claude

Let your Claude able to think

TinyZero

Clean, minimal, accessible reproduction of DeepSeek R1-Zero

TouchNet

A native-PyTorch library for large scale M-LLM (text/audio) training with tp/cp/dp/pp.

VideoChat

实时语音交互数字人，支持端到端语音方案（GLM-4-Voice - THG）和级联方案（ASR-LLM-TTS-THG）。可自定义形象与音色，无须训练，支持音色克隆，首包延迟低至3s。Real-time voice interactive digital human, supporting end-to-end voice solutions (GLM-4-Voice - THG) and cascaded solutions (ASR-LLM-TTS-THG). Customizable appearance and voice, supporting voice cloning, with initial package delay as low as 3s.

vlm_arm

机械臂+大模型+多模态=人机协作具身智能体

wenet

Production First and Production Ready End-to-End Speech Recognition Toolkit

Yolo_for_Wukong

a simple project to beat boss in Blackmyth Wukong, using yolo8 to detect boss movement and a script to react to certain detections