Update README.md
Browse files
README.md
CHANGED
@@ -23,8 +23,7 @@ Moreover, BAGEL demonstrates superior qualitative results in classical image‑e
|
|
23 |
Below is a showcase of BAGEL's qualitative performance.
|
24 |
|
25 |
|
26 |
-
This repository hosts the model weights for **BAGEL**.
|
27 |
-
For installation, usage instructions, and further documentation, please visit our [GitHub repository](https://github.com/bytedance-seed/BAGEL).
|
28 |
|
29 |
|
30 |
|
@@ -49,7 +48,7 @@ For installation, usage instructions, and further documentation, please visit ou
|
|
49 |
| **IntelligentBench** (↑) | 14.9 | 57.6 | 44.0 | **55.3** |
|
50 |
|
51 |
## License
|
52 |
-
BAGEL is licensed under the Apache 2.0 license. It is finetuned from [Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct)
|
53 |
|
54 |
## ✍️ Citation
|
55 |
```bibtex
|
|
|
23 |
Below is a showcase of BAGEL's qualitative performance.
|
24 |
|
25 |
|
26 |
+
This repository hosts the model weights for **BAGEL**. For installation, usage instructions, and further documentation, please visit our [GitHub repository](https://github.com/bytedance-seed/BAGEL).
|
|
|
27 |
|
28 |
|
29 |
|
|
|
48 |
| **IntelligentBench** (↑) | 14.9 | 57.6 | 44.0 | **55.3** |
|
49 |
|
50 |
## License
|
51 |
+
BAGEL is licensed under the Apache 2.0 license. It is finetuned from [Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) and [siglip-so400m-14-980-flash-attn2-navit](https://huggingface.co/HuggingFaceM4/siglip-so400m-14-980-flash-attn2-navit) model, and uses the [FLUX.1-schnell VAE model](https://huggingface.co/black-forest-labs/FLUX.1-schnell), all under Apache 2.0.
|
52 |
|
53 |
## ✍️ Citation
|
54 |
```bibtex
|