Commit
•
09f76c2
1
Parent(s):
c53413e
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,6 +1,7 @@
|
|
| 1 |
---
|
| 2 |
datasets:
|
| 3 |
- lmms-lab/LLaVA-NeXT-Video-SFT-Data
|
|
|
|
| 4 |
language:
|
| 5 |
- en
|
| 6 |
library_name: transformers
|
|
@@ -112,6 +113,8 @@ model-index:
|
|
| 112 |
value: 70.5
|
| 113 |
name: accuracy
|
| 114 |
verified: true
|
|
|
|
|
|
|
| 115 |
---
|
| 116 |
|
| 117 |
|
|
@@ -128,7 +131,7 @@ model-index:
|
|
| 128 |
|
| 129 |
## Model Summary
|
| 130 |
|
| 131 |
-
The LLaVA-
|
| 132 |
|
| 133 |
- **Repository:** [LLaVA-VL/LLaVA-NeXT](https://github.com/LLaVA-VL/LLaVA-NeXT?tab=readme-ov-file)
|
| 134 |
- **Point of Contact:** [Yuanhan Zhang](https://zhangyuanhan-ai.github.io/)
|
|
|
|
| 1 |
---
|
| 2 |
datasets:
|
| 3 |
- lmms-lab/LLaVA-NeXT-Video-SFT-Data
|
| 4 |
+
- lmms-lab/LLaVA-OneVision-Data
|
| 5 |
language:
|
| 6 |
- en
|
| 7 |
library_name: transformers
|
|
|
|
| 113 |
value: 70.5
|
| 114 |
name: accuracy
|
| 115 |
verified: true
|
| 116 |
+
base_model:
|
| 117 |
+
- lmms-lab/llava-onevision-qwen2-7b-si
|
| 118 |
---
|
| 119 |
|
| 120 |
|
|
|
|
| 131 |
|
| 132 |
## Model Summary
|
| 133 |
|
| 134 |
+
The LLaVA-Video models are 7/72B parameter models trained on [LLaVA-Video-178K](https://huggingface.co/datasets/lmms-lab/LLaVA-NeXT-Video-SFT-Data), based on Qwen2 language model with a context window of 32K tokens.
|
| 135 |
|
| 136 |
- **Repository:** [LLaVA-VL/LLaVA-NeXT](https://github.com/LLaVA-VL/LLaVA-NeXT?tab=readme-ov-file)
|
| 137 |
- **Point of Contact:** [Yuanhan Zhang](https://zhangyuanhan-ai.github.io/)
|