Update README.md
Browse files
README.md
CHANGED
|
@@ -27,11 +27,24 @@ license: mit
|
|
| 27 |
- A **novel alignment algorithm MM-DPO**.
|
| 28 |
- **Two new benchmarks**.
|
| 29 |
|
| 30 |
-
Our dataset and algorithms enable consistent performance improvements across **10 dimensions** and **27 benchmarks
|
| 31 |
<p align="center">
|
| 32 |
<img src="https://cdn-uploads.huggingface.co/production/uploads/623d8ca4c29adf5ef6175615/8nVZQd8bfB6NJIixCv6_X.png" width="80%" />
|
| 33 |
</p>
|
| 34 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35 |
## Citation
|
| 36 |
|
| 37 |
If you find it useful for your research and applications, please cite related papers/blogs using this BibTeX:
|
|
|
|
| 27 |
- A **novel alignment algorithm MM-DPO**.
|
| 28 |
- **Two new benchmarks**.
|
| 29 |
|
| 30 |
+
Our dataset and algorithms enable consistent performance improvements across **10 dimensions** and **27 benchmarks**.
|
| 31 |
<p align="center">
|
| 32 |
<img src="https://cdn-uploads.huggingface.co/production/uploads/623d8ca4c29adf5ef6175615/8nVZQd8bfB6NJIixCv6_X.png" width="80%" />
|
| 33 |
</p>
|
| 34 |
|
| 35 |
+
|
| 36 |
+
## Use
|
| 37 |
+
|
| 38 |
+
### Intended use
|
| 39 |
+
|
| 40 |
+
The model was trained on [MM-RLHF data](https://huggingface.co/datasets/yifanzhang114/MM-RLHF) and have the ability to interact with images, multi-image and videos.
|
| 41 |
+
|
| 42 |
+
**Feel free to share your generations in the Community tab!**
|
| 43 |
+
|
| 44 |
+
### Generation
|
| 45 |
+
|
| 46 |
+
We provide the simple generation process for using our model. For more details, you could refer to [Github](https://github.com/yfzhang114/MM-RLHF).
|
| 47 |
+
|
| 48 |
## Citation
|
| 49 |
|
| 50 |
If you find it useful for your research and applications, please cite related papers/blogs using this BibTeX:
|