Instructions to use deepseek-ai/JanusFlow-1.3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use deepseek-ai/JanusFlow-1.3B with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import MultiModalityCausalLM model = MultiModalityCausalLM.from_pretrained("deepseek-ai/JanusFlow-1.3B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download processor_config.json from deepseek-ai/JanusFlow-1.3B: direct link, hf CLI and curl.
- Browser
- Download file 369 Bytes
-
https://huggingface.co/deepseek-ai/JanusFlow-1.3B/resolve/main/processor_config.json
- Command line
-
hf download hf://deepseek-ai/JanusFlow-1.3B/processor_config.json
-
curl -L -o processor_config.json https://huggingface.co/deepseek-ai/JanusFlow-1.3B/resolve/main/processor_config.json
369 Bytes
| { | |
| "add_special_token": false, | |
| "ignore_id": -100, | |
| "image_end_tag": "<image_end>", | |
| "image_tag": "<image_placeholder>", | |
| "mask_prompt": true, | |
| "num_image_tokens": 576, | |
| "processor_class": "VLChatProcessor", | |
| "sft_format": "deepseek_old", | |
| "image_gen_tag": "<\uff5cbegin\u2581of\u2581generation\uff5c>", | |
| "image_start_tag": "<image_beg>" | |
| } |