Hongyun Qiu's repositories
AFFiNE
There can be more than Notion and Miro. AFFiNE(pronounced [ə‘fain]) is a next-gen knowledge base that brings planning, sorting and creating all together. Privacy first, open-source, customizable and ready to use.
anything-llm
Open-source ChatGPT equivalent experience for both open and close source LLMs, embedders, and vector databases. Supports unlimited documents, threads, and concurrent users and management all in a very clean UI.
astrometry.net
Astrometry.net -- automatic recognition of astronomical images
atopile
Design circuit boards with code! ✨ Get software-like design reuse 🚀, validation, version control and collaboration in hardware; starting with electronics ⚡️
Chinese-LLaMA-Alpaca
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
DenseDiffusion
Official Pytorch Implementation of DenseDiffusion (ICCV 2023)
generative-models
Generative Models by Stability AI
indi
INDI Core Library Repository
indi-3rdparty
INDI 3rd Party drivers repository
lerobot
🤗 LeRobot: State-of-the-art Machine Learning for Real-World Robotics in Pytorch
lit-gpt
Implementation of Falcon, StableLM, Pythia, INCITE language models based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
LLaMA2-Accessory
An Open-source Toolkit for LLM Development
LlamaGen
Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation
llm.c
LLM training in simple, raw C/CUDA
nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
NExT-GPT
Code and models for NExT-GPT: Any-to-Any Multimodal Large Language Model
openvla
OpenVLA: An open-source vision-language-action model for robotic manipulation.
QUARCS_phd2
PHD2 Guiding
segment-anything-2
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
supervision
We write your reusable computer vision tools. 💜
TinyLlama
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
UnIVAL
Official implementation of UnIVAL: Unified Model for Image, Video, Audio and Language Tasks.
VILA
VILA - a multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and laptops)
WizardLM
Family of instruction-following LLMs powered by Evol-Instruct: WizardLM, WizardCoder and WizardMath