Update README.md
Browse files
README.md
CHANGED
|
@@ -2,8 +2,10 @@
|
|
| 2 |
language:
|
| 3 |
- zh
|
| 4 |
- en
|
| 5 |
-
library_name: adapter-transformers
|
| 6 |
pipeline_tag: visual-question-answering
|
|
|
|
|
|
|
|
|
|
| 7 |
---
|
| 8 |
|
| 9 |
# Model
|
|
@@ -11,7 +13,7 @@ pipeline_tag: visual-question-answering
|
|
| 11 |
llava-qwen1.5-4b-chat is a lightweight multimodal models base on [LLaVA architecture](https://llava-vl.github.io/).
|
| 12 |
- Language Model: [Qwen/Qwen1.5-4B-Chat](https://huggingface.co/Qwen/Qwen1.5-4B-Chat)
|
| 13 |
- Vision Encoder: [google/siglip-so400m-patch14-384](https://huggingface.co/google/siglip-so400m-patch14-384)
|
| 14 |
-
- Paramters
|
| 15 |
|
| 16 |
## Evaluation
|
| 17 |
### MMBench
|
|
|
|
| 2 |
language:
|
| 3 |
- zh
|
| 4 |
- en
|
|
|
|
| 5 |
pipeline_tag: visual-question-answering
|
| 6 |
+
datasets:
|
| 7 |
+
- Lin-Chen/ShareGPT4V
|
| 8 |
+
- liuhaotian/LLaVA-Pretrain
|
| 9 |
---
|
| 10 |
|
| 11 |
# Model
|
|
|
|
| 13 |
llava-qwen1.5-4b-chat is a lightweight multimodal models base on [LLaVA architecture](https://llava-vl.github.io/).
|
| 14 |
- Language Model: [Qwen/Qwen1.5-4B-Chat](https://huggingface.co/Qwen/Qwen1.5-4B-Chat)
|
| 15 |
- Vision Encoder: [google/siglip-so400m-patch14-384](https://huggingface.co/google/siglip-so400m-patch14-384)
|
| 16 |
+
- Total Paramters: 4,388,102,720
|
| 17 |
|
| 18 |
## Evaluation
|
| 19 |
### MMBench
|