Update README.md
Browse files
README.md
CHANGED
@@ -39,7 +39,7 @@ Building on these advances, **Ovis2.5-9B** achieves an average score of 78.3 on
|
|
39 |
|
40 |
**Key Features**
|
41 |
* **Native-Resolution Perception** — NaViT vision encoder preserves fine details and global structure without lossy tiling.
|
42 |
-
* **Deep-Reasoning Capability** — Optional *thinking mode* for self-checking and revision beyond linear CoT.
|
43 |
* **Chart & Document OCR** — State-of-the-art at its scale for complex chart analysis, document understanding (including tables and forms), and OCR.
|
44 |
* **Broad Task Coverage** — Demonstrates leading performance on image reasoning, video understanding, and grounding benchmarks, showcasing strong general multimodal capability.
|
45 |
|
|
|
39 |
|
40 |
**Key Features**
|
41 |
* **Native-Resolution Perception** — NaViT vision encoder preserves fine details and global structure without lossy tiling.
|
42 |
+
* **Deep-Reasoning Capability** — Optional *thinking mode* for self-checking and revision beyond linear CoT. *Thinking budget* supported.
|
43 |
* **Chart & Document OCR** — State-of-the-art at its scale for complex chart analysis, document understanding (including tables and forms), and OCR.
|
44 |
* **Broad Task Coverage** — Demonstrates leading performance on image reasoning, video understanding, and grounding benchmarks, showcasing strong general multimodal capability.
|
45 |
|