Update README.md
Browse files
README.md
CHANGED
|
@@ -10,6 +10,10 @@ tags:
|
|
| 10 |
## Introduction
|
| 11 |
Ovis is a novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings. For a comprehensive introduction, please refer to [Ovis paper](https://arxiv.org/abs/2405.20797) and [Ovis GitHub](https://github.com/AIDC-AI/Ovis).
|
| 12 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
## Model
|
| 14 |
Ovis can be instantiated with popular LLMs (e.g., Qwen, Llama3). We provide the following pretrained Ovis MLLMs:
|
| 15 |
|
|
|
|
| 10 |
## Introduction
|
| 11 |
Ovis is a novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings. For a comprehensive introduction, please refer to [Ovis paper](https://arxiv.org/abs/2405.20797) and [Ovis GitHub](https://github.com/AIDC-AI/Ovis).
|
| 12 |
|
| 13 |
+
<div align="center">
|
| 14 |
+
<img src="https://github.com/AIDC-AI/Ovis/raw/main/docs/ovis-illustration.png" width="100%" />
|
| 15 |
+
</div>
|
| 16 |
+
|
| 17 |
## Model
|
| 18 |
Ovis can be instantiated with popular LLMs (e.g., Qwen, Llama3). We provide the following pretrained Ovis MLLMs:
|
| 19 |
|