ezalos

setfit

Efficient few-shot learning with Sentence Transformers

ngrok

Unified ingress for developers

phonetics

Implementation of phonetic algorithm in python

champ-for-windows

Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance

PaDiM-Anomaly-Detection-Localization-master

This is an unofficial implementation of the paper “PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization”.

authx

Ready-to-use and customizable Authentications and Oauth2 management for FastAPI ✨

T-Rex

API for T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy

sqlmodel

SQL databases in Python, designed for simplicity, compatibility, and robustness.

openface

Face recognition with deep neural networks.

facenet-pytorch

Pretrained Pytorch face detection (MTCNN) and facial recognition (InceptionResnet) models

quickwit

Cloud-native search engine for observability. An open-source alternative to Datadog, Elasticsearch, Loki, and Tempo.

InstantID

InstantID : Zero-shot Identity-Preserving Generation in Seconds 🔥

chainlit

Build Conversational AI in minutes ⚡️

s5cmd

Parallel S3 and local filesystem execution tool.

MemGPT

Create LLM agents with long-term memory and custom tools 📚🦙

LLMs-from-scratch

Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step

insightface

State-of-the-art 2D and 3D Face Analysis Project

gpt-researcher

GPT based autonomous agent that does online comprehensive research on any given topic

AlphaCodium

Official implementation for the paper: "Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering""

Trans2k

QFormer

The official repo for [TPAMI'23] "Vision Transformer with Quadrangle Attention"

ml-ferret

tiktoken

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

COMM

Pytorch code for paper From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models

LLaVA

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

shikra

CogVLM

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

DECOLA

Code release for "Language-conditioned Detection Transformer"

insanely-fast-whisper

open-datagen