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 2 weeks ago
Alternatives and similar repositories for OmegaViT:
Users that are interested in OmegaViT are comparing it to the libraries listed below
- BH hackathon☆14Updated last year
- A forest of autonomous agents.☆19Updated 3 months ago
- Transform unstructured documents into actionable, structured data with enterprise-grade precision and reliability, ready for large-scale …☆19Updated 2 weeks ago
- The original BabyAGI, updated with LiteLLM and no vector database reliance (csv instead)☆21Updated 7 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 11 months ago
- ☆14Updated last year
- ☆21Updated 6 months ago
- The world's first fully automated VC fund.☆23Updated 2 weeks ago
- alternative way to calculating self attention☆18Updated 11 months ago
- Implementation of SelfExtend from the paper "LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning" from Pytorch and Zeta☆13Updated 5 months ago
- Lego for GRPO☆27Updated last month
- A list of language models with permissive licenses such as MIT or Apache 2.0☆24Updated 2 months ago
- Modified Beam Search with periodical restart☆12Updated 7 months ago
- AgentParse is a high-performance parsing library designed to map various structured data formats (such as Pydantic models, JSON, YAML, an…☆13Updated 2 weeks ago
- Example implementation of Iteration of Tought - Gives a star if you like the project☆41Updated 4 months ago
- BUD-E (Buddy) is an open-source voice assistant framework that facilitates seamless interaction with AI models and APIs, enabling the cre…☆19Updated 6 months ago
- Proteus is an experimental platform that combines the power of Large Language Models with the Genesis physics engine☆21Updated 4 months ago
- OmniByteFormer is a generalized Transformer model that can process any type of data by converting it into byte sequences, bypassing tradi…☆10Updated last week
- ☆16Updated 2 months ago
- NewsAgent is an enterprise-grade news aggregation agent designed to fetch, query, and summarize news from multiple sources at scale.☆16Updated 2 weeks ago
- Uses a Gradio interface to stream coding related responses from local and cloud based large language models. Pulls context from GitHub Re…☆21Updated last month
- An open source replication of the stawberry method that leverages Monte Carlo Search with PPO and or DPO☆29Updated last week
- Fine-tune copilot based on your codebase☆12Updated last year
- ☆38Updated 9 months ago
- Small Multimodal Vision Model "Imp-v1-3b" trained using Phi-2 and Siglip.☆17Updated last year
- The Benefits of a Concise Chain of Thought on Problem Solving in Large Language Models☆22Updated 5 months ago
- Repository to create traveling waves integrate special information through time☆51Updated last month
- Groq-powered MAD: The first work to explore Multi-Agent Debate with Large Language Models :D☆12Updated 10 months ago
- Very minimal (and stateless) agent framework☆43Updated 3 months ago
- The Swarm Ecosystem☆20Updated 9 months ago