thenlper commited on
Commit
a62d4ef
1 Parent(s): 615ba56

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -6
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](https://arxiv.org/pdf/2407.19669)**.
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/general-text-embedding/): 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
 
@@ -3720,9 +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.xxxxx},
3724
  archivePrefix={arXiv},
3725
  primaryClass={cs.CL},
3726
- url={https://arxiv.org/abs/2412.xxxxx},
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
+ ```