Agora-Lab-AI / OmegaViT
OmegaViT (ΩViT) is a cutting-edge vision transformer architecture that combines multi-query attention, rotary embeddings, state space modeling, and mixture of experts to achieve superior performance across various computer vision tasks.
☆14Updated this week
Alternatives and similar repositories for OmegaViT:
Users that are interested in OmegaViT are comparing it to the libraries listed below
- alternative way to calculating self attention☆18Updated 9 months ago
- BH hackathon☆14Updated 11 months ago
- The original BabyAGI, updated with LiteLLM and no vector database reliance (csv instead)☆21Updated 5 months ago
- A list of language models with permissive licenses such as MIT or Apache 2.0☆24Updated 3 weeks ago
- Transform unstructured documents into actionable, structured data with enterprise-grade precision and reliability, ready for large-scale …☆19Updated this week
- Using multiple LLMs for ensemble Forecasting☆16Updated last year
- The Benefits of a Concise Chain of Thought on Problem Solving in Large Language Models☆21Updated 3 months ago
- A public implementation of the ReLoRA pretraining method, built on Lightning-AI's Pytorch Lightning suite.☆33Updated last year
- An open source replication of the stawberry method that leverages Monte Carlo Search with PPO and or DPO☆28Updated last week
- ☆18Updated 4 months ago
- never forget anything again! combine AI and intelligent tooling for a local knowledge base to track catalogue, annotate, and plan for you…☆37Updated 10 months ago
- A forest of autonomous agents.☆19Updated last month
- Modified Beam Search with periodical restart☆12Updated 6 months ago
- Very minimal (and stateless) agent framework☆41Updated 2 months ago
- Proteus is an experimental platform that combines the power of Large Language Models with the Genesis physics engine☆21Updated 3 months ago
- ☆14Updated 11 months ago
- Implementation of SelfExtend from the paper "LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning" from Pytorch and Zeta☆13Updated 4 months ago
- Visual RAG using less than 300 lines of code.☆27Updated last year
- BUD-E (Buddy) is an open-source voice assistant framework that facilitates seamless interaction with AI models and APIs, enabling the cre…☆17Updated 5 months ago
- The Swarm Ecosystem☆18Updated 7 months ago
- ☆15Updated 5 months ago
- The world's first fully automated VC fund.☆20Updated this week
- ☆13Updated 3 months ago