MaybeShewill-CV

LLaMA-Factory

Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)

llama3

The official Meta Llama 3 GitHub site

unsloth

Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

llama3-from-scratch

llama3 implementation one matrix multiplication at a time

LivePortrait

Bring portraits to life!

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.

HivisionIDPhotos

⚡️HivisionIDPhotos: a lightweight and efficient AI ID photos tools. 一个轻量级的AI证件照制作算法。

duix.ai

GOT-OCR2.0

Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

automq

AutoMQ is a cloud-first alternative to Kafka by decoupling durability to S3 and EBS. 10x cost-effective. Autoscale in seconds. Single-digit ms latency.

Depth-Anything-V2

Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

OpenGlass

Turn any glasses into AI-powered smart glasses

LyCORIS

Lora beYond Conventional methods, Other Rank adaptation Implementations for Stable diffusion.

c-style

My favorite C programming practices.

VILA

VILA - a multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and laptops)

FluxMusic

Text-to-Music Generation with Rectified Flow Transformers

FoundationPose

[CVPR 2024 Highlight] FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects

nano-llama31

nanoGPT style version of Llama 3.1

GLEE

[CVPR2024 Highlight]GLEE: General Object Foundation Model for Images and Videos at Scale

accelerated_features

Implementation of XFeat (CVPR 2024). Do you need robust and fast local feature extraction? You are in the right place!

recurrentgemma

Open weights language model from Google DeepMind, based on Griffin.

meta

Header-only, non-intrusive and macro-free runtime reflection system in C++

cppguidebook

小彭老师领衔编写，现代C++的中文百科全书

flash-diffusion

Official implementation of ⚡ Flash Diffusion ⚡: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation

Inf-DiT

Official implementation of Inf-DiT: Upsampling Any-Resolution Image with Memory-Efficient Diffusion Transformer

asio-grpc

Asynchronous gRPC with Asio/unified executors

Tianji

从零学习，制作懂人情世故的大语言模型

B-LoRA

Implicit Style-Content Separation using B-LoRA

OmniTokenizer

OmniTokenizer: one model and one weight for image-video joint tokenization.

Cascade-CLIP

Official implement of ICML2024 Cascade-CLIP: Cascaded Vision-Language Embeddings Alignment for Zero-Shot Semantic Segmentation