vikhyatk
/

moondream2

Image-Text-to-Text

text-generation

Model card Files Files and versions

vikhyatk commited on Sep 18, 2025

Commit

ac3ef11

·

verified ·

1 Parent(s): 27feae9

Update README.md

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -1,6 +1,7 @@
 ---
 license: apache-2.0
 pipeline_tag: image-text-to-text
 ---
 ⚠️ This repository contains the latest version of Moondream 2, our previous generation model. The latest version of Moondream is [Moondream 3 (Preview)](https://huggingface.co/moondream/moondream3-preview).
@@ -84,4 +85,4 @@ print(f"Found {len(points)} person(s)")
 4. Improved text understanding (e.g. OCRBench increased from 58.3 to 61.2)
 5. Improved object detection, especially for small objects (e.g. COCO up from 30.5 to 51.2)
 6. Fixed token streaming bug affecting multi-byte unicode characters
-7. gpt-fast style `compile()` now supported in HF Transformers implementation

 ---
 license: apache-2.0
 pipeline_tag: image-text-to-text
+new_version: moondream/moondream3-preview
 ---
 ⚠️ This repository contains the latest version of Moondream 2, our previous generation model. The latest version of Moondream is [Moondream 3 (Preview)](https://huggingface.co/moondream/moondream3-preview).
 4. Improved text understanding (e.g. OCRBench increased from 58.3 to 61.2)
 5. Improved object detection, especially for small objects (e.g. COCO up from 30.5 to 51.2)
 6. Fixed token streaming bug affecting multi-byte unicode characters
+7. gpt-fast style `compile()` now supported in HF Transformers implementation