Update README.md
Browse files
README.md
CHANGED
|
@@ -4,6 +4,8 @@ pipeline_tag: image-text-to-text
|
|
| 4 |
datasets:
|
| 5 |
- YipengZhang/LLaVA-UHD-v2-SFT-Data
|
| 6 |
library_name: transformers
|
|
|
|
|
|
|
| 7 |
---
|
| 8 |
|
| 9 |
<br>
|
|
@@ -19,6 +21,9 @@ by constructing and integrating a high resolution feature pyramid.
|
|
| 19 |
**Model date:**
|
| 20 |
LLaVA-UHD v2 was trained in November 2024.
|
| 21 |
|
|
|
|
|
|
|
|
|
|
| 22 |
**Paper or resources for more information:**
|
| 23 |
https://github.com/thunlp/LLaVA-UHD
|
| 24 |
|
|
|
|
| 4 |
datasets:
|
| 5 |
- YipengZhang/LLaVA-UHD-v2-SFT-Data
|
| 6 |
library_name: transformers
|
| 7 |
+
base_model:
|
| 8 |
+
- lmsys/vicuna-7b-v1.5
|
| 9 |
---
|
| 10 |
|
| 11 |
<br>
|
|
|
|
| 21 |
**Model date:**
|
| 22 |
LLaVA-UHD v2 was trained in November 2024.
|
| 23 |
|
| 24 |
+
**Base LLM Model:**
|
| 25 |
+
lmsys/vicuna-7b-v1.5
|
| 26 |
+
|
| 27 |
**Paper or resources for more information:**
|
| 28 |
https://github.com/thunlp/LLaVA-UHD
|
| 29 |
|