Instructions to use timm/deepseek_vit_412m_enc.deepseek_v4_flash_vision_exp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use timm/deepseek_vit_412m_enc.deepseek_v4_flash_vision_exp with timm:
import timm model = timm.create_model("hf-hub:timm/deepseek_vit_412m_enc.deepseek_v4_flash_vision_exp", pretrained=True) - Transformers
How to use timm/deepseek_vit_412m_enc.deepseek_v4_flash_vision_exp with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="timm/deepseek_vit_412m_enc.deepseek_v4_flash_vision_exp")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("timm/deepseek_vit_412m_enc.deepseek_v4_flash_vision_exp", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from timm/deepseek_vit_412m_enc.deepseek_v4_flash_vision_exp: direct link, hf CLI and curl.
- Browser
- Download file 834 Bytes
-
https://huggingface.co/timm/deepseek_vit_412m_enc.deepseek_v4_flash_vision_exp/resolve/main/config.json
- Command line
-
hf download hf://timm/deepseek_vit_412m_enc.deepseek_v4_flash_vision_exp/config.json
-
curl -L -o config.json https://huggingface.co/timm/deepseek_vit_412m_enc.deepseek_v4_flash_vision_exp/resolve/main/config.json
834 Bytes
| { | |
| "architecture": "deepseek_vit_412m_enc", | |
| "num_classes": 0, | |
| "num_features": 1024, | |
| "global_pool": "align", | |
| "model_args": { | |
| "global_pool": "align", | |
| "out_features": 4096 | |
| }, | |
| "pretrained_cfg": { | |
| "tag": "deepseek_v4_flash_vision_exp", | |
| "custom_load": false, | |
| "input_size": [ | |
| 3, | |
| 392, | |
| 392 | |
| ], | |
| "min_input_size": [ | |
| 3, | |
| 126, | |
| 126 | |
| ], | |
| "fixed_input_size": false, | |
| "interpolation": "bicubic", | |
| "crop_pct": 1.0, | |
| "crop_mode": "border", | |
| "mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "num_classes": 0, | |
| "pool_size": null, | |
| "first_conv": "patch_embed.proj", | |
| "classifier": null, | |
| "license": "mit", | |
| "origin_url": "https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp" | |
| } | |
| } |