quinwu

llama.cpp

LLM inference in C/C++

llama

Inference code for LLaMA models

faiss

A library for efficient similarity search and clustering of dense vectors.

vllm

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

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

detr

End-to-End Object Detection with Transformers

flash-attention

Fast and memory-efficient exact attention

llama-gpt

A self-hosted, offline, ChatGPT-like chatbot. Powered by Llama 2. 100% private, with no data leaving your device. New: Code Llama support!

bisheng

Bisheng is an open LLM devops platform for next generation AI applications.

FastSAM

Fast Segment Anything

mae

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

Baichuan-7B

A large-scale 7B pretraining language model developed by BaiChuan-Inc.

GroundingDINO

Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

Segment-Everything-Everywhere-All-At-Once

[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"

mmpretrain

OpenMMLab Pre-training Toolbox and Benchmark

transformer-deploy

Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀

WebGLM

WebGLM: An Efficient Web-enhanced Question Answering System (KDD 2023)

lang-segment-anything

SAM with text prompt

segment-anything-fast

A batched offline inference oriented version of segment-anything

SoM

Set-of-Mark Prompting for LMMs

GPT4RoI

GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest

llm-search

Querying local documents, powered by LLM

FlashRank

Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cross-encoders and more. Created by Prithivi Da, open for PRs & Collaborations.

sft_datasets

开源SFT数据集整理,随时补充

TinySAM

Official PyTorch implementation of "TinySAM: Pushing the Envelope for Efficient Segment Anything Model"

chat2plot

chat to visualization with LLM

segment-anything-tensorrt

segment_anything_tensorrt

Accelerate segment anything model inference using Tensorrt 8.6.1.6

BYZER-RETRIEVAL

Byzer-retrieval is a distributed retrieval system which designed as a backend for LLM RAG (Retrieval Augmented Generation). The system supports both BM25 retrieval algorithm and vector retrieval algorithm.

triton-server

triton server with segment anything(SAM)