Update README.md

README.md

@@ -7,7 +7,7 @@ Moondream is a small vision language model designed to run efficiently on edge d
 
 [Website](https://moondream.ai/) / [Demo](https://moondream.ai/playground) / [GitHub](https://github.com/vikhyat/moondream)
 
-This repository contains the latest (**2025-01-09**) release of Moondream, as well as [historical releases](https://huggingface.co/vikhyatk/moondream2/blob/main/versions.txt). The model is updated frequently, so we recommend specifying a revision as shown below if you're using it in a production application.
+This repository contains the latest (**2025-03-27**) release of Moondream, as well as [historical releases](https://huggingface.co/vikhyatk/moondream2/blob/main/versions.txt). The model is updated frequently, so we recommend specifying a revision as shown below if you're using it in a production application.
 
 
 **Usage**
@@ -18,7 +18,7 @@ from PIL import Image
 
 model = AutoModelForCausalLM.from_pretrained(
     "vikhyatk/moondream2",
-    revision="2025-01-09",
+    revision="2025-03-27",
     trust_remote_code=True,
     # Uncomment to run on GPU.
     # device_map={"": "cuda"}
@@ -47,4 +47,15 @@ print(f"Found {len(objects)} face(s)")
 print("\nPointing: 'person'")
 points = model.point(image, "person")["points"]
 print(f"Found {len(points)} person(s)")
-```
+```
+
+**Changelog**
+
+**2025-03-27**
+
+1. Added support for long-form captioning.
+2. Improved counting accuracy (e.g. CountBenchQA increased from 80 to 86.4)
+3. Improved text understanding (e.g. OCRBench increased from 58.3 to 61.2)
+4. Improved object detection, especially for small objects
+5. Fixed token streaming bug affecting multi-byte unicode characters
+6. gpt-fast style `compile()` now supported in HF Transformers implementation