yoosan

ollama

Get up and running with Llama 3.2, Mistral, Gemma 2, and other large language models.

Real-Time-Voice-Cloning

Clone a voice in 5 seconds to generate arbitrary speech in real-time

grok-1

Grok open release

generative-models

Generative Models by Stability AI

ragflow

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

marker

Convert PDF to markdown quickly with high accuracy

rembg

Rembg is a tool to remove images background

surya

OCR, layout analysis, reading order, table recognition in 90+ languages

magika

Detect file content types with deep learning

gemma.cpp

lightweight, standalone C++ inference engine for Google's Gemma models.

InternVL

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

gemma_pytorch

The official PyTorch implementation of Google's Gemma models

torchtune

PyTorch native finetuning library

VAR

[NeurIPS 2024 Oral][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!

transformer-debugger

Queryable

Run OpenAI's CLIP and Apple's MobileCLIP model on iOS to search photos.

gemma

Open weights LLM from Google DeepMind.

mpire

A Python package for easy multiprocessing, but faster than multiprocessing

SearchEngine

搜索引擎原理

minisora

MiniSora: A community aims to explore the implementation path and future development direction of Sora.

WonderJourney

multimodal-prompt-learning

[CVPR 2023] Official repository of paper titled "MaPLe: Multi-modal Prompt Learning".

text-dedup

All-in-one text de-duplication

distrifuser

[CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models

llm-compressor

Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

KVQuant

[NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization

vattention

Dynamic Memory Management for Serving LLMs without PagedAttention

Full-Segment-Anything

This is Pytorch Implementation Code for adding new features in code of Segment-Anything. Here, the features support batch-input on the full-grid prompt (automatic mask generation) with post-processing: removing duplicated or small regions and holes, under flexible input image size

the-stack-v2

Code for the curation of The Stack v2 and StarCoder2 training data

GeoReasoner

GeoReasoner: Geo-localization with Reasoning in Street Views using a Large Vision-Language Mode