Open-Bee
/

Bee-8B-RL

Image-Text-to-Text

feature-extraction

Fully-Open-MLLMs

Model card Files Files and versions

uyzhang commited on Oct 15

Commit

48a3023

·

1 Parent(s): 052577a

update readme.md

Files changed (1) hide show

README.md +3 -2

README.md CHANGED Viewed

@@ -99,9 +99,10 @@ print(output_text)
 ## Experimental Results
-<div align="center">
 <img src="assets/results.png" alt="logo"/>
-</div>
 1.  **New State-of-the-Art:** Bee-8B establishes a new performance standard for fully open MLLMs, proving highly competitive with recent semi-open models across a wide array of benchmarks.
 2.  **Excellence in Complex Reasoning:** Thanks to the CoT-enriched Honey-Data-15M, Bee-8B shows its most significant advancements in complex math and reasoning. It achieves top scores on challenging benchmarks like **MathVerse**, **LogicVista**, and **DynaMath**.

 ## Experimental Results
+<figure align="center">
 <img src="assets/results.png" alt="logo"/>
+<figcaption>Evaluation of Bee-8B against other MLLMs. We distinguish between fully open (*) and semi-open (†) models. The <strong>top</strong> and <strong>second-best</strong> scores for each benchmark are highlighted.</figcaption>
+</figure>
 1.  **New State-of-the-Art:** Bee-8B establishes a new performance standard for fully open MLLMs, proving highly competitive with recent semi-open models across a wide array of benchmarks.
 2.  **Excellence in Complex Reasoning:** Thanks to the CoT-enriched Honey-Data-15M, Bee-8B shows its most significant advancements in complex math and reasoning. It achieves top scores on challenging benchmarks like **MathVerse**, **LogicVista**, and **DynaMath**.