Instructions to use xiaomoguhzz/VisionEncoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use xiaomoguhzz/VisionEncoder with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("xiaomoguhzz/VisionEncoder", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download data/s2_20pct/counts.json from xiaomoguhzz/VisionEncoder: direct link, hf CLI and curl.
- Browser
- Download file 664 Bytes
-
https://huggingface.co/xiaomoguhzz/VisionEncoder/resolve/main/data/s2_20pct/counts.json
- Command line
-
hf download hf://xiaomoguhzz/VisionEncoder/data/s2_20pct/counts.json
-
curl -L -o counts.json https://huggingface.co/xiaomoguhzz/VisionEncoder/resolve/main/data/s2_20pct/counts.json
664 Bytes
| { | |
| "image": { | |
| "training_records": 147718, | |
| "unique_media": 122247 | |
| }, | |
| "video": { | |
| "training_records": 220011, | |
| "unique_media": 105108, | |
| "frame_index_records": 105108, | |
| "paths_without_frame_index": 0, | |
| "unique_media_by_source": { | |
| "0_30_s_academic_v0_1": 11639, | |
| "0_30_s_youtube_v0_1": 24441, | |
| "1_2_m_academic_v0_1": 4627, | |
| "1_2_m_youtube_v0_1": 17575, | |
| "2_3_m_academic_v0_1": 3122, | |
| "2_3_m_youtube_v0_1": 17620, | |
| "30_60_s_academic_v0_1": 10200, | |
| "30_60_s_youtube_v0_1": 15884 | |
| } | |
| }, | |
| "frame_cache": { | |
| "frames": 64, | |
| "resolution": 384, | |
| "jpeg_quality": 95, | |
| "sheet_cols": 16 | |
| } | |
| } | |