Update README.md (#1)
Browse files- Update README.md (aaef7c5417d13f4d63710e25855c82097005a2a4)
- Update README.md (4d1e22f6d1416b7ddca11422b41d5004bdb47172)
Co-authored-by: Victor Sanh <[email protected]>
README.md
CHANGED
|
@@ -1,9 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# LVM
|
| 2 |
|
| 3 |
This is the model implementation of the CVPR 2024 'Sequential Modeling Enables Scalable Learning for Large Vision Models'. (https://arxiv.org/abs/2312.00785)
|
| 4 |
|
| 5 |
LVM is a vision pretraining model that converts various kinds of visual data into visual sentences and performs next-token prediction autoregressively. It is compatible with both GPU and TPU.
|
| 6 |
|
|
|
|
|
|
|
| 7 |
LVM is built on top of [OpenLLaMA](https://github.com/openlm-research/open_llama) (an autoregressive model) and [OpenMuse](https://github.com/huggingface/open-muse) (a VQGAN that converts images into visual tokens).
|
| 8 |
|
| 9 |
This was trained in collaboration with HuggingFace. Thanks [Victor Sanh](https://huggingface.co/VictorSanh) for the support in this project.
|
|
@@ -27,4 +36,4 @@ If you found LVM useful in your research or applications, please cite our work u
|
|
| 27 |
journal={arXiv preprint arXiv:2312.00785},
|
| 28 |
year={2023}
|
| 29 |
}
|
| 30 |
-
\`\`\`
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- image
|
| 5 |
+
- video
|
| 6 |
+
inference: false
|
| 7 |
+
---
|
| 8 |
# LVM
|
| 9 |
|
| 10 |
This is the model implementation of the CVPR 2024 'Sequential Modeling Enables Scalable Learning for Large Vision Models'. (https://arxiv.org/abs/2312.00785)
|
| 11 |
|
| 12 |
LVM is a vision pretraining model that converts various kinds of visual data into visual sentences and performs next-token prediction autoregressively. It is compatible with both GPU and TPU.
|
| 13 |
|
| 14 |
+
You can try out the demo [here](https://huggingface.co/spaces/Emma02/LVM).
|
| 15 |
+
|
| 16 |
LVM is built on top of [OpenLLaMA](https://github.com/openlm-research/open_llama) (an autoregressive model) and [OpenMuse](https://github.com/huggingface/open-muse) (a VQGAN that converts images into visual tokens).
|
| 17 |
|
| 18 |
This was trained in collaboration with HuggingFace. Thanks [Victor Sanh](https://huggingface.co/VictorSanh) for the support in this project.
|
|
|
|
| 36 |
journal={arXiv preprint arXiv:2312.00785},
|
| 37 |
year={2023}
|
| 38 |
}
|
| 39 |
+
\`\`\`
|