Ma-Dan's repositories
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
FlappyBird
Less than 100 Kilobytes. Works for Android 5.1 and above
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
libllm
Efficient inference of large language models.
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。
mlc-llm
Universal LLM Deployment Engine with ML Compilation
mllm
Fast Multimodal LLM on Mobile Devices
mnn-llm
llm deploy project based mnn.
Native-LLM-for-Android
Demonstration of running a native LLM on Android device.
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
Thinking-Claude
Let your Claude able to think
TinyZero
Clean, minimal, accessible reproduction of DeepSeek R1-Zero
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
Zero-Chatgpt
从0开始,将chatgpt的技术路线跑一遍。
Zero-Qwen-VL
训练一个对中文支持更好的LLaVA模型,并开源训练代码和数据。