Update README.md
Browse files
README.md
CHANGED
|
@@ -8,6 +8,9 @@ tags:
|
|
| 8 |
---
|
| 9 |
# Omnivision
|
| 10 |
|
|
|
|
|
|
|
|
|
|
| 11 |
## Introduction
|
| 12 |
|
| 13 |
Omnivision is a compact, sub-billion (968M) multimodal model for processing both visual and text inputs, optimized for edge devices. Improved on LLaVA's architecture, it features:
|
|
@@ -16,7 +19,7 @@ Omnivision is a compact, sub-billion (968M) multimodal model for processing both
|
|
| 16 |
- **Trustworthy Result**: Reduces hallucinations using **DPO** training from trustworthy data.
|
| 17 |
|
| 18 |
**Quick Links:**
|
| 19 |
-
1. Interactive Demo in our [Hugging Face Space](https://huggingface.co/spaces/NexaAIDev/omnivlm-dpo-demo).
|
| 20 |
2. [Quickstart for local setup](#how-to-use-on-device)
|
| 21 |
3. Learn more in our [Blogs](https://nexa.ai/blogs/omni-vision)
|
| 22 |
|
|
|
|
| 8 |
---
|
| 9 |
# Omnivision
|
| 10 |
|
| 11 |
+
## Latest Update
|
| 12 |
+
- [Nov 21, 2024] We improved Omnivision-968M based on your feedback! 🚀 Test the preview in our [Hugging Face Space](https://huggingface.co/spaces/NexaAIDev/omnivlm-dpo-demo). The updated GGUF and **safetensors** will be released after final alignment tweaks.
|
| 13 |
+
|
| 14 |
## Introduction
|
| 15 |
|
| 16 |
Omnivision is a compact, sub-billion (968M) multimodal model for processing both visual and text inputs, optimized for edge devices. Improved on LLaVA's architecture, it features:
|
|
|
|
| 19 |
- **Trustworthy Result**: Reduces hallucinations using **DPO** training from trustworthy data.
|
| 20 |
|
| 21 |
**Quick Links:**
|
| 22 |
+
1. Interactive Demo in our [Hugging Face Space](https://huggingface.co/spaces/NexaAIDev/omnivlm-dpo-demo). (Updated 2024 Nov 21)
|
| 23 |
2. [Quickstart for local setup](#how-to-use-on-device)
|
| 24 |
3. Learn more in our [Blogs](https://nexa.ai/blogs/omni-vision)
|
| 25 |
|