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.
☆12Updated this week
Alternatives and similar repositories for OmegaViT:
Users that are interested in OmegaViT are comparing it to the libraries listed below
- Transform unstructured documents into actionable, structured data with enterprise-grade precision and reliability, ready for large-scale …☆17Updated this week
- BH hackathon☆14Updated 9 months ago
- An open source replication of the stawberry method that leverages Monte Carlo Search with PPO and or DPO☆27Updated this week
- The original BabyAGI, updated with LiteLLM and no vector database reliance (csv instead)☆21Updated 3 months ago
- alternative way to calculating self attention☆18Updated 8 months ago
- The Benefits of a Concise Chain of Thought on Problem Solving in Large Language Models☆21Updated 2 months ago
- Modified Beam Search with periodical restart☆12Updated 4 months ago
- ☆18Updated 2 months ago
- never forget anything again! combine AI and intelligent tooling for a local knowledge base to track catalogue, annotate, and plan for you…☆36Updated 8 months ago
- A forest of autonomous agents.☆18Updated this week
- A public implementation of the ReLoRA pretraining method, built on Lightning-AI's Pytorch Lightning suite.☆33Updated 10 months ago
- A list of language models with permissive licenses such as MIT or Apache 2.0☆24Updated 2 months ago
- Exploration using DSPy to optimize modules to maximize performance on the OpenToM dataset☆14Updated 10 months ago
- ☆15Updated 10 months ago
- BUD-E (Buddy) is an open-source voice assistant framework that facilitates seamless interaction with AI models and APIs, enabling the cre…☆17Updated 3 months ago
- The Swarm Ecosystem☆19Updated 5 months ago
- ☆14Updated 4 months ago
- Implementation of MambaFormer in Pytorch ++ Zeta from the paper: "Can Mamba Learn How to Learn? A Comparative Study on In-Context Learnin…☆20Updated this week
- ☆13Updated 11 months ago
- ☆16Updated 11 months ago
- tiny_fnc_engine is a minimal python library that provides a flexible engine for calling functions extracted from a LLM.☆38Updated 4 months ago
- ☆13Updated last month
- The world's first fully automated VC fund.☆18Updated this week
- Proteus is an experimental platform that combines the power of Large Language Models with the Genesis physics engine☆18Updated last month
- ☆26Updated 10 months ago
- Chat WebUI is an easy-to-use user interface for interacting with AI, and it comes with multiple useful built-in tools.☆15Updated 2 months ago
- Very minimal (and stateless) agent framework☆41Updated 2 weeks ago
- A Python implementation of an agent swarm system that works with local LLM servers. The system allows you to create multiple agents that …☆11Updated 2 months ago