Hugging Face's logo

PharMolix
/
Mol-VL-7B

Safetensors
qwen2_vl
Model card Files
xet
 Community
leofansq commited on
Commit
cb8157d
·
verified ·
1 Parent(s): 72caaad

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -5,7 +5,7 @@ Mol-VL is a Vision-Language Model for Optical Chemical Structure Understanding (
5
 
6
  To take advantage of existing pretrained VLMs, we adopt the weights from Qwen2-VL. Mol-VL-7B is further finetuned on [Vis-CheBI20](https://huggingface.co/datasets/PharMolix/Vis-CheBI20) training set.
7
 
8
- For technical details, please refer to [OCSU](https://arxiv.org/pdf/2501.15415). Training and evaluation scripts will be available recently, stay tuned!
9
 
10
  If you find our work useful in your research, please consider citing:
11
 
 
5
 
6
  To take advantage of existing pretrained VLMs, we adopt the weights from Qwen2-VL. Mol-VL-7B is further finetuned on [Vis-CheBI20](https://huggingface.co/datasets/PharMolix/Vis-CheBI20) training set.
7
 
8
+ For technical details, please refer to [OCSU](https://arxiv.org/pdf/2501.15415). Training and evaluation scripts are available at [Github](https://github.com/PharMolix/OCSU).
9
 
10
  If you find our work useful in your research, please consider citing:
11