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
Download processor_config.json from KU-AGI/FiRe-SFT: direct link, hf CLI and curl.
- Browser
- Download file 334 Bytes
-
https://huggingface.co/KU-AGI/FiRe-SFT/resolve/main/processor_config.json
- Command line
-
hf download hf://KU-AGI/FiRe-SFT/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/KU-AGI/FiRe-SFT/resolve/main/processor_config.json
334 Bytes
| { | |
| "add_special_token": false, | |
| "ignore_id": -100, | |
| "image_end_tag": "<end_of_image>", | |
| "image_start_tag": "<begin_of_image>", | |
| "image_tag": "<image_placeholder>", | |
| "mask_prompt": true, | |
| "num_image_tokens": 576, | |
| "pad_tag": "<\uff5c\u2581pad\u2581\uff5c>", | |
| "processor_class": "VLChatProcessor", | |
| "sft_format": "deepseek" | |
| } | |