Instructions to use BLIP3o/BLIP3o-Model-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use BLIP3o/BLIP3o-Model-8B with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("BLIP3o/BLIP3o-Model-8B", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -13,6 +13,24 @@ This is BLIP3o-8B checkpoint trained on the **open source** data.
|
|
| 13 |
| 8B (paper reported) | 30 million open-source + 30 million proprietary data | 0.84 | 81.60 | 0.62 |
|
| 14 |
|
| 15 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
### Download
|
| 17 |
|
| 18 |
```
|
|
|
|
| 13 |
| 8B (paper reported) | 30 million open-source + 30 million proprietary data | 0.84 | 81.60 | 0.62 |
|
| 14 |
|
| 15 |
|
| 16 |
+
|
| 17 |
+
Here is the category results for WISE
|
| 18 |
+
|
| 19 |
+
| Model | Pretrain Data | Cultural | Time | Space | Biology | Physics | Chemistry | Overall |
|
| 20 |
+
| :--------------: | :-------------------------: | :------: | :--: | :---: | :-----: | :-----: | :-------: | :-----: |
|
| 21 |
+
| 8B (open source) | 30 million open-source data | 0.49 | 0.51 | 0.63 | 0.54 | 0.63 | 0.37 | 0.52 |
|
| 22 |
+
| 8B (paper reported) | 30 million open-source + 30 million proprietary data| 0.63 | 0.57 | 0.70 | 0.62 | 0.66 | 0.51 | 0.62 |
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
|
| 34 |
### Download
|
| 35 |
|
| 36 |
```
|