opendatalab
/

ChartVerse-2B

Image-Text-to-Text

vision-language

chart-understanding

Model card Files Files and versions

starriver030515 commited on 7 days ago

Commit

90d8cfe

·

verified ·

1 Parent(s): 4e7620b

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -18,7 +18,7 @@ datasets:
 - opendatalab/ChartVerse-RL-40K
 ---
-**ChartVerse-2B** is a compact yet powerful Vision Language Model (VLM) specialized for complex chart reasoning, developed as part of the **[opendatalab/ChartVerse](https://huggingface.co/collections/opendatalab/chartverse)** project. For more details about our method, datasets, and full model series, please visit our [GitHub Repository](https://github.com/starriver030515/ChartVerse) and [Project Page](https://chartverse.github.io).
 Despite its 2B parameter size, ChartVerse-2B achieves superior performance compared to larger chart-specific models like ECD-7B, START-7B, and Chart-R1-7B, demonstrating that high-quality training data can substantially offset model size limitations.

 - opendatalab/ChartVerse-RL-40K
 ---
+**ChartVerse-2B** is a compact yet powerful Vision Language Model (VLM) specialized for complex chart reasoning, developed as part of the **[opendatalab/ChartVerse](https://huggingface.co/collections/opendatalab/chartverse)** project. For more details about our method, datasets, and full model series, please visit our [Project Page](https://chartverse.github.io).
 Despite its 2B parameter size, ChartVerse-2B achieves superior performance compared to larger chart-specific models like ECD-7B, START-7B, and Chart-R1-7B, demonstrating that high-quality training data can substantially offset model size limitations.