Feature Extraction
Transformers
Safetensors
English
hyperstyler
style-transfer
authorship
custom_code
Instructions to use JKSHINPG/HyperStyler with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use JKSHINPG/HyperStyler with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="JKSHINPG/HyperStyler", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("JKSHINPG/HyperStyler", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from JKSHINPG/HyperStyler: direct link, hf CLI and curl.
- Browser
- Download file 883 Bytes
-
https://huggingface.co/JKSHINPG/HyperStyler/resolve/main/config.json
- Command line
-
hf download hf://JKSHINPG/HyperStyler/config.json
-
curl -L -o config.json https://huggingface.co/JKSHINPG/HyperStyler/resolve/main/config.json
883 Bytes
| { | |
| "architectures": [ | |
| "HyperStylerModel" | |
| ], | |
| "model_type": "hyperstyler", | |
| "auto_map": { | |
| "AutoConfig": "configuration_hyperstyler.HyperStylerConfig", | |
| "AutoModel": "modeling_hyperstyler.HyperStylerModel" | |
| }, | |
| "base_model_name": "google/t5-v1_1-large", | |
| "max_encoder_len": 80, | |
| "max_decoder_len": 80, | |
| "styler_config": { | |
| "ctrl_dim": 768, | |
| "use_hypernet": true, | |
| "hypernet_config": { | |
| "target_layers": [ | |
| "crossattn", | |
| "ffn" | |
| ], | |
| "num_prefix": 5, | |
| "rank": 32, | |
| "parameter_efficiency_mode": false, | |
| "bias": false, | |
| "search_config": "MHA", | |
| "dropout": 0.1 | |
| }, | |
| "use_stylonavigator": true, | |
| "stylo_navigator_config": { | |
| "dropout": 0.1, | |
| "temperature": 1.0 | |
| } | |
| }, | |
| "style_model_name": "AnnaWegmann/Style-Embedding", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.50.0" | |
| } |