404805854

Deep-Live-Cam

real time face swap and one-click video deepfake with only a single image

gpt-2

Code for the paper "Language Models are Unsupervised Multitask Learners"

yoga

Yoga is an embeddable layout engine targeting web standards.

PathFinding.js

A comprehensive path-finding library for grid based games

AI-Scientist

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

FlagEmbedding

Retrieval and Retrieval-augmented LLMs

streaming-llm

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

GroundingDINO

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

FunASR

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

Chinese-CLIP

Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.

ollama-python

Ollama Python library

sapiens

High-resolution models for human tasks.

speech-to-speech

Speech To Speech: an effort for an open-sourced and modular GPT4-o

taffy

A high performance rust-powered UI layout library

YOLOP

You Only Look Once for Panopitic Driving Perception.（MIR2022）

KalmanFilter

This is a Kalman filter used to calculate the angle, rate and bias from from the input of an accelerometer/magnetometer and a gyroscope.

InternVideo

[ECCV2024] Video Foundation Models & Data for Multimodal Understanding

SpeechGPT

SpeechGPT Series: Speech Large Language Models

Show-o

Repository for Show-o, One Single Transformer to Unify Multimodal Understanding and Generation.

AgentK

An autoagentic AGI that is self-evolving and modular.

VITA

✨✨VITA: Towards Open-Source Interactive Omni Multimodal LLM

AnyGPT

Code for "AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling"

humor

Code for ICCV 2021 paper "HuMoR: 3D Human Motion Model for Robust Pose Estimation"

micrograd

The Autograd Engine

DQN_play_sekiro

DQN_play_sekiro

NExT-Chat

The code of the paper "NExT-Chat: An LMM for Chat, Detection and Segmentation".

LLM101n-CN

LLM101n: Let's build a Storyteller 中文版

Flash-VStream

This is the official implementation of "Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams"

COCO-UniHuman

ollama

Get up and running with Llama 3.1, Mistral, Gemma 2, and other large language models.