Text-to-Image
Transformers
Safetensors
multi_modality
image-generation
multimodal
unified-model
janus
reasoning
FiRe
Instructions to use KU-AGI/FiRe-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use KU-AGI/FiRe-SFT with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import MultiModalityCausalLM model = MultiModalityCausalLM.from_pretrained("KU-AGI/FiRe-SFT", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add `library_name` to metadata
Browse filesThis PR adds `library_name: transformers` to the model card metadata. The model's config file indicates a Transformers-compatible architecture (`MultiModalityCausalLM`) and includes `transformers_version`, so this metadata is appropriate. No other content changes are needed since the model card already contains the paper, project page, code links, and relevant sections.
README.md
CHANGED
|
@@ -1,14 +1,15 @@
|
|
| 1 |
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
base_model: deepseek-ai/Janus-Pro
|
|
|
|
| 4 |
pipeline_tag: text-to-image
|
|
|
|
| 5 |
tags:
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
| 12 |
---
|
| 13 |
|
| 14 |
<div align="center">
|
|
@@ -73,4 +74,4 @@ We sincerely thank the authors of [Janus-Series](https://github.com/deepseek-ai/
|
|
| 73 |
journal={arXiv preprint arXiv:2604.13491},
|
| 74 |
year={2026}
|
| 75 |
}
|
| 76 |
-
```
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
base_model: deepseek-ai/Janus-Pro
|
| 3 |
+
license: apache-2.0
|
| 4 |
pipeline_tag: text-to-image
|
| 5 |
+
library_name: transformers
|
| 6 |
tags:
|
| 7 |
+
- image-generation
|
| 8 |
+
- multimodal
|
| 9 |
+
- unified-model
|
| 10 |
+
- janus
|
| 11 |
+
- reasoning
|
| 12 |
+
- FiRe
|
| 13 |
---
|
| 14 |
|
| 15 |
<div align="center">
|
|
|
|
| 74 |
journal={arXiv preprint arXiv:2604.13491},
|
| 75 |
year={2026}
|
| 76 |
}
|
| 77 |
+
```
|