Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,28 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
datasets:
|
4 |
+
- turing-motors/LLaVA-Pretrain-JA
|
5 |
+
language:
|
6 |
+
- ja
|
7 |
---
|
8 |
+
|
9 |
+
# LLaVA-JP Model Card
|
10 |
+
This is a pretrained checkpoint, you can use it to instruct tune your multimodal models.
|
11 |
+
|
12 |
+
Check out the instructions [here](https://github.com/tosiyuki/LLaVA-JP)
|
13 |
+
|
14 |
+
## Model details
|
15 |
+
**Model type:**
|
16 |
+
LLaVA-JP is a vision-language model that can converse about input images.<br>
|
17 |
+
This model is an LVLM model trained using [google/siglip-so400m-patch14-384](https://huggingface.co/google/siglip-so400m-patch14-384) as the image encoder and [llm-jp/llm-jp-1.3b-v1.0](https://huggingface.co/llm-jp/llm-jp-1.3b-v1.0) as the text decoder. supports the input of 768 x 768 high resolution images by scaling_on_scales method.
|
18 |
+
|
19 |
+
## Training dataset
|
20 |
+
- [LLaVA-Pretrain-JA](https://huggingface.co/datasets/turing-motors/LLaVA-Pretrain-JA)
|
21 |
+
|
22 |
+
## Acknowledgement
|
23 |
+
- [LLaVA](https://llava-vl.github.io/)
|
24 |
+
- [LLM-jp](https://llm-jp.nii.ac.jp/)
|
25 |
+
- [scaling_on_scales](https://github.com/bfshi/scaling_on_scales/tree/master)
|
26 |
+
|
27 |
+
## License
|
28 |
+
Apache-2.0
|