Fix 2025-04-14 date
#77
by
joaompalmeiro
- opened
README.md
CHANGED
|
@@ -63,7 +63,7 @@ print(f"Found {len(points)} person(s)")
|
|
| 63 |
* **Reinforcement Learning Enhancements**
|
| 64 |
RL fine-tuning applied across 55 vision-language tasks to reinforce grounded reasoning and detection capabilities, with a roadmap to expand to \~120 tasks in the next update.
|
| 65 |
|
| 66 |
-
**2025-04-
|
| 67 |
|
| 68 |
1. Improved chart understanding (ChartQA up from 74.8 to 77.5, 82.2 with PoT)
|
| 69 |
2. Added temperature and nucleus sampling to reduce repetitive outputs
|
|
|
|
| 63 |
* **Reinforcement Learning Enhancements**
|
| 64 |
RL fine-tuning applied across 55 vision-language tasks to reinforce grounded reasoning and detection capabilities, with a roadmap to expand to \~120 tasks in the next update.
|
| 65 |
|
| 66 |
+
**2025-04-14** ([full release notes](https://moondream.ai/blog/moondream-2025-04-14-release))
|
| 67 |
|
| 68 |
1. Improved chart understanding (ChartQA up from 74.8 to 77.5, 82.2 with PoT)
|
| 69 |
2. Added temperature and nucleus sampling to reduce repetitive outputs
|