metadata
license: apache-2.0
language:
- en
base_model:
- Qwen/Qwen2-VL-2B-Instruct
pipeline_tag: image-text-to-text
library_name: transformers
tags:
- text-generation-inference
- vl
- vQ
- Chem-Qwen
**ChemQwen-vL [ Qwen of Chemistry Vision ] **
ChemQwen-vL is a vision-language model fine-tuned based on the Qwen2VL-2B Instruct model. It has been trained using the International Chemical Identifier (InChI) format and is optimized for chemical component identification. The model excels at generating the InChI and providing descriptions of chemical compounds based on their images.
Its architecture, derived from Qwen2-VL, can handle images of arbitrary resolutions by mapping them into a dynamic number of visual tokens. This offers a more human-like visual processing experience. The model operates in a multi-modal framework, combining image-text-text capabilities.