Hugging Face's logo

Alibaba-NLP
/
gme-Qwen2-VL-2B-Instruct

Sentence Similarity
sentence-transformers
Safetensors
Transformers
English
Chinese
qwen2_vl
image-text-to-text
mteb
Qwen2-VL
vidore
custom_code
Eval Results (legacy)
Model card Files
xet
 Community
26
thenlper commited on
Commit
8584213
·
verified ·
1 Parent(s): c013eb4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -3590,12 +3590,12 @@ model-index:
3590
  ---
3591
 
3592
  <p align="center">
3593
- <iframe src="images/gme_logo.pdf" width="auto" height="auto"></iframe>
3594
  </p>
3595
 
3596
  <p align="center"><b>GME: General Multimodal Embeddings</b></p>
3597
 
3598
- ## GME-Qwen2VL-2B
3599
 
3600
  We are excited to present `GME-Qwen2VL` series of unified **multimodal embedding models**,
3601
  which are based on the advanced [Qwen2-VL](https://huggingface.co/collections/Qwen/qwen2-vl-66cee7455501d7126940800d) multimodal large language models (MLLMs).
 
3590
  ---
3591
 
3592
  <p align="center">
3593
+ <img src="images/gme_logo.png" alt="GME Logo" style="width: 100%; max-width: 250px;">
3594
  </p>
3595
 
3596
  <p align="center"><b>GME: General Multimodal Embeddings</b></p>
3597
 
3598
+ ## GME-Qwen2-VL-2B
3599
 
3600
  We are excited to present `GME-Qwen2VL` series of unified **multimodal embedding models**,
3601
  which are based on the advanced [Qwen2-VL](https://huggingface.co/collections/Qwen/qwen2-vl-66cee7455501d7126940800d) multimodal large language models (MLLMs).