Update README.md
Browse files
README.md
CHANGED
|
@@ -1,7 +1,27 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
pipeline_tag: any-to-any
|
| 4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
# Model Card for UniMedVL
|
| 6 |
|
| 7 |
UniMedVL is the first unified medical foundation model for seamless multimodal understanding and generation, following a clinically-inspired Observation-Knowledge-Analysis framework.
|
|
@@ -41,5 +61,6 @@ The model can be directly used for:
|
|
| 41 |
|
| 42 |
- **Clinical Decision Making**: This model is for research purposes only and should NOT be used for actual clinical diagnosis or treatment decisions
|
| 43 |
|
|
|
|
| 44 |
|
| 45 |
-
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
pipeline_tag: any-to-any
|
| 4 |
+
language:
|
| 5 |
+
- en
|
| 6 |
+
- zh
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
base_model:
|
| 10 |
+
- ByteDance-Seed/BAGEL-7B-MoT
|
| 11 |
+
- Qwen/Qwen2.5-VL-7B-Instruct
|
| 12 |
+
tags:
|
| 13 |
+
- medical
|
| 14 |
+
- vision-language
|
| 15 |
+
- multimodal
|
| 16 |
+
- unified-model
|
| 17 |
+
- medical-vqa
|
| 18 |
+
- text-to-image
|
| 19 |
+
- image-to-text
|
| 20 |
+
- medical-understanding
|
| 21 |
+
- report-generation
|
| 22 |
+
- interleaved-multimodal
|
| 23 |
+
- modality-transfer
|
| 24 |
+
---
|
| 25 |
# Model Card for UniMedVL
|
| 26 |
|
| 27 |
UniMedVL is the first unified medical foundation model for seamless multimodal understanding and generation, following a clinically-inspired Observation-Knowledge-Analysis framework.
|
|
|
|
| 61 |
|
| 62 |
- **Clinical Decision Making**: This model is for research purposes only and should NOT be used for actual clinical diagnosis or treatment decisions
|
| 63 |
|
| 64 |
+
## Acknowledgments
|
| 65 |
|
| 66 |
+
We sincerely thank the [Bagel](https://github.com/jmistral/bagel) project for providing the foundational framework upon which our code and model training are built.
|