Update README.md
Browse files
README.md
CHANGED
@@ -3613,7 +3613,7 @@ The `GME` models support three types of input: **text**, **image**, and **image-
|
|
3613 |
|
3614 |
**Developed by**: Tongyi Lab, Alibaba Group
|
3615 |
|
3616 |
-
**Paper**: GME: Improving Universal Multimodal Retrieval by Multimodal LLMs
|
3617 |
|
3618 |
|
3619 |
## Model List
|
@@ -3678,7 +3678,7 @@ We validated the performance on our universal multimodal retrieval benchmark (**
|
|
3678 |
|
3679 |
The [MTEB Leaderboard](https://huggingface.co/spaces/mteb/leaderboard) English tab shows the text embeddings performence of our model.
|
3680 |
|
3681 |
-
**More detailed experimental results can be found in the [paper](
|
3682 |
|
3683 |
|
3684 |
## Limitations
|
@@ -3701,7 +3701,7 @@ We encourage and value diverse applications of GME models and continuous enhance
|
|
3701 |
|
3702 |
In addition to the open-source [GME](https://huggingface.co/collections/Alibaba-NLP/gme-models-67667e092da3491f630964d6) series models, GME series models are also available as commercial API services on Alibaba Cloud.
|
3703 |
|
3704 |
-
- [MultiModal Embedding Models](https://help.aliyun.com/zh/model-studio/developer-reference/
|
3705 |
|
3706 |
Note that the models behind the commercial APIs are not entirely identical to the open-source models.
|
3707 |
|
@@ -3720,9 +3720,9 @@ If you find our paper or models helpful, please consider cite:
|
|
3720 |
title={GME: Improving Universal Multimodal Retrieval by Multimodal LLMs},
|
3721 |
author={Zhang, Xin and Zhang, Yanzhao and Xie, Wen and Li, Mingxin and Dai, Ziqi and Long, Dingkun and Xie, Pengjun and Zhang, Meishan and Li, Wenjie and Zhang, Min},
|
3722 |
year={2024},
|
3723 |
-
eprint={2412.
|
3724 |
archivePrefix={arXiv},
|
3725 |
primaryClass={cs.CL},
|
3726 |
-
url={
|
3727 |
}
|
3728 |
-
```
|
|
|
3613 |
|
3614 |
**Developed by**: Tongyi Lab, Alibaba Group
|
3615 |
|
3616 |
+
**Paper**: [GME: Improving Universal Multimodal Retrieval by Multimodal LLMs](http://arxiv.org/abs/2412.16855)
|
3617 |
|
3618 |
|
3619 |
## Model List
|
|
|
3678 |
|
3679 |
The [MTEB Leaderboard](https://huggingface.co/spaces/mteb/leaderboard) English tab shows the text embeddings performence of our model.
|
3680 |
|
3681 |
+
**More detailed experimental results can be found in the [paper](http://arxiv.org/abs/2412.16855)**.
|
3682 |
|
3683 |
|
3684 |
## Limitations
|
|
|
3701 |
|
3702 |
In addition to the open-source [GME](https://huggingface.co/collections/Alibaba-NLP/gme-models-67667e092da3491f630964d6) series models, GME series models are also available as commercial API services on Alibaba Cloud.
|
3703 |
|
3704 |
+
- [MultiModal Embedding Models](https://help.aliyun.com/zh/model-studio/developer-reference/multimodal-embedding-api-reference?spm=a2c4g.11186623.0.0.321c1d1cqmoJ5C): The `multimodal-embedding-v1` model service is available.
|
3705 |
|
3706 |
Note that the models behind the commercial APIs are not entirely identical to the open-source models.
|
3707 |
|
|
|
3720 |
title={GME: Improving Universal Multimodal Retrieval by Multimodal LLMs},
|
3721 |
author={Zhang, Xin and Zhang, Yanzhao and Xie, Wen and Li, Mingxin and Dai, Ziqi and Long, Dingkun and Xie, Pengjun and Zhang, Meishan and Li, Wenjie and Zhang, Min},
|
3722 |
year={2024},
|
3723 |
+
eprint={2412.16855},
|
3724 |
archivePrefix={arXiv},
|
3725 |
primaryClass={cs.CL},
|
3726 |
+
url={http://arxiv.org/abs/2412.16855},
|
3727 |
}
|
3728 |
+
```
|