Update README.md
Browse files
README.md
CHANGED
|
@@ -91,6 +91,10 @@ They demonstrate superior performance across CUA benchmarks. In particular, <b>O
|
|
| 91 |
establishing a new state-of-the-art (SOTA) among open-source models and surpassing OpenAI CUA (GPT-4o). Both models also have strong grounding performance, OpenCUA-32B achieves 59.6% on [OSWorld-G](https://osworld-grounding.github.io/) and 55.3% on [Screenspot-Pro](https://arxiv.org/abs/2504.07981).
|
| 92 |
</div>
|
| 93 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 94 |
### Key Features
|
| 95 |
|
| 96 |
- **Superior Computer-Use Capablity**: Able to execute multi-step computer-use actions with effective planning and reasoning
|
|
|
|
| 91 |
establishing a new state-of-the-art (SOTA) among open-source models and surpassing OpenAI CUA (GPT-4o). Both models also have strong grounding performance, OpenCUA-32B achieves 59.6% on [OSWorld-G](https://osworld-grounding.github.io/) and 55.3% on [Screenspot-Pro](https://arxiv.org/abs/2504.07981).
|
| 92 |
</div>
|
| 93 |
|
| 94 |
+
## 📢 Updates
|
| 95 |
+
- 2025-10-12: <span style="font-weight:bold">[OpenCUA-7B-exl2](https://huggingface.co/sujitvasanth/OpenCUA-7B-exl2) is now live!</span> ⚡️
|
| 96 |
+
Thanks to [Sujit Vasanth](https://huggingface.co/sujitvasanth) for producing a quantized **exllamav2** version of OpenCUA-7B — enabling much faster inference with lower VRAM usage.
|
| 97 |
+
|
| 98 |
### Key Features
|
| 99 |
|
| 100 |
- **Superior Computer-Use Capablity**: Able to execute multi-step computer-use actions with effective planning and reasoning
|