Y-J-Ju
/

SaHa-Qwen2-VL-2B-Instruct

Sentence Similarity

image-text-to-text

Model card Files Files and versions

Y-J-Ju commited on Aug 5, 2025

Commit

730959a

·

1 Parent(s): cef1243

update readme

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -142,7 +142,7 @@ The model's performance was evaluated on the MMEB evaluation set, which includes
 The SaHa-Qwen2-VL-2B-Instruct model achieves state-of-the-art performance in its parameter class on the MMEB benchmark, outperforming methods that rely on large-scale contrastive pre-training.
 | Model | Params | Classification | Retrieval | VQA | Grounding | **IND** | **OND** | **Overall Avg.** |
-| :--- | :---: | :---: | :---: | :---: | :---: | :---: |
 | Ours (SaHa-Qwen2-VL-2B) | 2.2B | 65.4 | 70.0 | 59.1 | 83.0 | **71.2** | **62.1** | **67.1** |

 The SaHa-Qwen2-VL-2B-Instruct model achieves state-of-the-art performance in its parameter class on the MMEB benchmark, outperforming methods that rely on large-scale contrastive pre-training.
 | Model | Params | Classification | Retrieval | VQA | Grounding | **IND** | **OND** | **Overall Avg.** |
+| :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
 | Ours (SaHa-Qwen2-VL-2B) | 2.2B | 65.4 | 70.0 | 59.1 | 83.0 | **71.2** | **62.1** | **67.1** |