update versions.txt

README.md

@@ -18,7 +18,7 @@ from PIL import Image
 
 model = AutoModelForCausalLM.from_pretrained(
     "vikhyatk/moondream2",
-    revision="2025-03-27",
+    revision="2025-04-14",
     trust_remote_code=True,
     # Uncomment to run on GPU.
     # device_map={"": "cuda"}
@@ -51,6 +51,10 @@ print(f"Found {len(points)} person(s)")
 
 ### Changelog
 
+**2025-04-15**
+
+(coming soon)
+
 **2025-03-27**
 
 1. Added support for long-form captioning
@@ -59,4 +63,4 @@ 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 mAP 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
+7. gpt-fast style `compile()` now supported in HF Transformers implementation

versions.txt

@@ -7,4 +7,5 @@
 2024-07-23
 2024-08-26
 2025-01-09
-2025-03-27
+2025-03-27
+2025-04-14