ganliqiang

unsloth

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

mPLUG-Owl

mPLUG-Owl: The Powerful Multi-modal Large Language Model Family

PicQ

PicQ: Demo for MiniCPM-V 2.6 to answer questions about images using natural language.

boxmot

BoxMOT: pluggable SOTA tracking modules for segmentation, object detection and pose estimation models

ms-swift

Use PEFT or Full-parameter to finetune 300+ LLMs or 60+ MLLMs. (Qwen2, GLM4v, Internlm2.5, Yi, Llama3.1, Llava-Video, Internvl2, MiniCPM-V-2.6, Deepseek, Baichuan2, Gemma2, Phi3-Vision, ...)

CogVLM

a state-of-the-art-level open visual language model | 多模态预训练模型

GLM-4

GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型

AISystem

AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

Depth-Anything-V2

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

LLaVA-pp

🔥🔥 LLaVA++: Extending LLaVA with Phi-3 and LLaMA-3 (LLaVA LLaMA-3, LLaVA Phi-3)

cambrian

Cambrian-1 is a family of multimodal LLMs with a vision-centric design.

FFmpeg

Mirror of https://git.ffmpeg.org/ffmpeg.git

inference

Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you need. With Xinference, you're empowered to run inference with any open-source language models, speech recognition models, and multimodal models, whether in the cloud, on-premises, or even on your laptop.

PLA

(CVPR 2023) PLA: Language-Driven Open-Vocabulary 3D Scene Understanding & (CVPR2024) RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understanding

dual-teacher

Official code for the NeurIPS 2023 paper "Switching Temporary Teachers for Semi-Supervised Semantic Segmentation"

mamba

The Fast Cross-Platform Package Manager

UniMatch

[CVPR 2023] Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation

semivl

[ECCV'24] Official Implementation of SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance

AllSpark

CVPR 2024: AllSpark: Reborn Labeled Features from Unlabeled in Transformer for Semi-Supervised Semantic Segmentation

ONE-PEACE

A general representation model across vision, audio, language modalities. Paper: ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities

LLaVA-UHD

LLaVA-UHD: an LMM Perceiving Any Aspect Ratio and High-Resolution Images

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

BakLLaVA

bitsandbytes

Accessible large language models via k-bit quantization for PyTorch.

llama-cpp-python

Python bindings for llama.cpp

lmdeploy

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

llama.cpp

LLM inference in C/C++

llm-awq

[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

Syndrone

Repository containing the code and tools required to build & smulate on the Syndrone dataset.