DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Repository Index
57,138 visible repositories in the index
1–24 of 44 · Most stars
Making large AI models cheaper, faster and more accessible
- deep-learning
- hpc
- large-scale
- data-parallelism
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
- artificial-intelligence
- attention-mechanism
- transformers
- computer-vision
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
- attention-mechanism
- deep-learning
- gpt
- gpt-2
🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐
- attention
- pytorch
- paper
- cbam
Open-source intelligence for the global theater. Track everything from the corporate/private jets of the wealthy, and spy satellites, to seismic events in one unified interface. Hook an AI agent up to have it parse through data and find previously unseen correlations. The knowledge is available to all but rarely aggregated in the open, until now.
- osint
- osint-resources
- asdb
- cctv
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
- bloom
- deep-learning
- distributed-systems
- language-models
A terminal spreadsheet multitool for discovering and arranging data
all kinds of text classification models and more with deep learning
- classification
- nlp
- fasttext
- textcnn
Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM
- artificial-intelligence
- attention-mechanisms
- deep-learning
- reinforcement-learning
TranslatedKorean AI-text humanizer: detects and rewrites translationese, mechanical parallelism, and 71 other AI tells — a Claude skill that polishes Korean text written by AI so it reads like human writing
- agent-skills
- ai-detection
- claude
- claude-code
A concise but complete full-attention transformer with a set of promising experimental features from various papers
- artificial-intelligence
- deep-learning
- attention-mechanism
- transformers
Red Ink - A one-stop Xiaohongshu image-and-text generator based on the 🍌Nano Banana Pro🍌, "One Sentence, One Image: Generate Xiaohongshu Text and Images."
- ai
- aigc
- content-generator
- social-media
Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch
- artificial-intelligence
- deep-learning
- attention-mechanism
- text-to-image
📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉
- flash-attention
- paged-attention
- tensorrt-llm
- vllm
DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (SVS & TTS); AAAI 2022; Official code
- text-to-speech
- diffusion-speedup
- tts
- aaai2022
A collection of important graph embedding, classification and representation learning papers with implementations.
- graph2vec
- classification-algorithm
- graph-kernels
- weisfeiler-lehman
A library that scrapes Linkedin for user data
- linkedin-scraper
- scraper
- profile
TranslatedAgent Skill for Refining AI-Generated Japanese into Natural Japanese
- agent-skills
- ai-writing
- claude-code
- codex
Multilingual Automatic Speech Recognition with word-level timestamps and confidence
We propose Prism, a dynamic sparse attention framework for natively training joint video-audio generation models at 2K.
- diffusion-models
- high-resolution
- sparse-attention
- video-generation
ObsPy: A Python Toolbox for seismology/seismological observatories.
- seismology
- python
- observatories
- science
Scalable, event-driven, deep-learning-friendly backtesting library
- reinforcement-learning
- deep-reinforcement-learning
- gym-environment
- openai-gym
Jelly is a recreational programming language inspired by J.