Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings.
| Date | Stars |
|---|---|
| 2026-07-24 | 1471 |
| 2026-07-25 | 1471 |
| 2026-07-28 | 1477 |
| 2026-07-30 | 1477 |
| 2026-07-31 | 1480 |
| 2026-08-09 | 1489 |
| 2026-08-18 | 1512 |
| 2026-08-19 | 1513 |
| 2026-08-21 | 1510 |
| 2026-08-22 | 1512 |
| 2026-08-24 | 1511 |
| 2026-08-25 | 1512 |
| 2026-08-30 | 1513 |
| 2026-09-02 | 1514 |
| 2026-09-03 | 1515 |
| 2026-09-04 | 1514 |
| 2026-09-07 | 1515 |
| 2026-09-10 | 1516 |
| 2026-09-13 | 1517 |
| 2026-09-14 | 1518 |
| 2026-09-15 | 1520 |
| 2026-09-16 | 1521 |
| 2026-09-18 | 1522 |
| 2026-09-20 | 1522 |
Today
— stars today
This week
+5 stars this week
This month
+12 stars this month
Momentum
0.0
growth rate 0.33%/day
# Ovis <div align="center"> <img src=docs/ovis_logo.png width="30%"/> </div> <br> <p align="center"> <a href="https://arxiv.org/abs/2508.11737"><img src="https://img.shields.io/badge/📖_Technical_Report-Ovis2.5-b31b1b.svg" alt="technical report"></a> <a href="https://huggingface.co/spaces/AIDC-AI/Ovis2.5-9B"><img src="https://img.shields.io/badge/🎨_HF_Spaces-AIDC--AI/Ovis2.5--9B-lightblack" alt="demo"></a> <a href="https://huggingface.co/collections/AIDC-AI/ovis25-689ec1474633b2aab8809335"><img src="https://img.shields.io/badge/🤗_Models-AIDC--AI/Ovis2.5-yellow" alt="models"></a> </p> ## Introduction Ovis (Open VISion) is a novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings. <div style="text-align: center;"> <img style="max-width: 100%;" src="docs/Ovis25_arch.png" alt="Ovis Illustration"/> </div> ## 🔥 We are hiring! We are looking for both interns and full-time researchers to join our team, focusing on multimodal understanding, generation, reasoning, AI agents, and unified multimodal models. If you are interested in exploring these exciting areas, please reach out to us at [email protected]. ## Release - [25/08/15] 🔥 Launch of [Ovis2.5-2B/9B](https://huggingface.co/AIDC-AI/Ovis2.5-9B), featuring native-resolution visual perception, enhanced reflective reasoning (*thinking mode*), and leading performance across STEM, chart analysis, grounding, and video understanding. - [25/03/25] 🔥 Announcing quantized versions of Ovis2 series, covering [Ovis2-2/4/8/16/34B](https://huggingface.co/AIDC-AI/Ovis2-34B-GPTQ-Int4)! - [25/01/26] 🔥 Launch of [Ovis2-1/2/4/8/16/34B](https://huggingface.co/AIDC-AI/Ovis2-34B), the latest version of Ovis models, featuring breakthrough small-model performance, enhanced reasoning capabilities, advanced video and multi-image processing, expanded multilingual OCR support, and improved high-resolution image handling. - [24/11/26] 🔥 Announcing [Ovis1.6-Gemma2-27B](https://huggingface.co/AIDC-AI/Ovis1.6-Gemma2-27B)! - [24/11/04] 🔥 Announcing quantized versions of Ovis1.6: [Ovis1.6-Gemma2-9B-GPTQ-Int4](https://huggingface.co/AIDC-AI/Ovis1.6-Gemma2-9B-GPTQ-Int4) and [Ovis1.6-Llama3.2-3B-GPTQ-Int4](https://huggingface.co/AIDC-AI/Ovis1.6-Llama3.2-3B-GPTQ-Int4)! - [24/10/22] 🔥 Announcing Ovis1.6-Llama3.2-3B ([Model](https://huggingface.co/AIDC-AI/Ovis1.6-Llama3.2-3B), [Demo](https://huggingface.co/spaces/AIDC-AI/Ovis1.6-Llama3.2-3B))! - [24/09/19] 🔥 Announcing Ovis1.6-Gemma2-9B ([Model](https://huggingface.co/AIDC-AI/Ovis1.6-Gemma2-9B), [Demo](https://huggingface.co/spaces/AIDC-AI/Ovis1.6-Gemma2-9B))! This release further enhances high-resolution image processing, is trained on a larger, more diverse, and higher-quality dataset, and refines the training process with DPO training following instruction-tuning. - [24/07/24] 🔥 Introducing Ovis1.5, featuring improved high-resolution image processing and optimized training data for enhanced performance. - [24/06/14] 🔥 Launch of Ovis1.0, the inaugural version of the Ovis model. ## Contents - [Ovis: Structural Embedding Alignment for Multimodal Large Language Model](#ovis-structural-embedding-alignment-for-multimodal-large-language-model) - [Release](#release) - [Contents](#contents) - [Model](#model) - [Performance](#performance) - [Install](#install) - [Inference](#inference) - [Model Fine-tuning](#model-fine-tuning) - [Citation](#citation) - [Team](#team) - [License](#license) - [Disclaimer](#disclaimer) ## Model Ovis can be instantiated with popular LLMs. We provide the following Ovis MLLMs: | Ovis MLLMs | ViT | LLM | Model Weights | Demo | |:-----------|:-----------------------:|:---------------------:|:-------------------------------------------------------:|:-----------------------------------------------------
Excerpt of 11,484 characters
Read on GitHub
44
10
Alibaba OSS · Alibaba Group Holding Limited · China
1
Mihai Chirculescu · Romania
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:37bf358edc71fff9, topic:multimodal, topic:vision-language-model, desc:multimodal
matched fp:37bf358edc71fff9, topic:qwen, readme:model weights, readme:technical report