Instructions to use longvideotool/LongVT-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use longvideotool/LongVT-SFT with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("longvideotool/LongVT-SFT") model = AutoModelForMultimodalLM.from_pretrained("longvideotool/LongVT-SFT", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download dataset.yaml from longvideotool/LongVT-SFT: direct link, hf CLI and curl.
- Browser
- Download file 657 Bytes
-
https://huggingface.co/longvideotool/LongVT-SFT/resolve/main/dataset.yaml
- Command line
-
hf download hf://longvideotool/LongVT-SFT/dataset.yaml
-
curl -L -o dataset.yaml https://huggingface.co/longvideotool/LongVT-SFT/resolve/main/dataset.yaml
657 Bytes
| datasets: | |
| - data_folder: '' | |
| data_type: parquet | |
| path: /pfs/training-data/kaichenzhang/data/VideoTool/gemini_cot/gemini_cot.parquet | |
| - data_folder: '' | |
| data_type: parquet | |
| path: /pfs/training-data/kaichenzhang/data/VideoTool/gemini_cot/gemini_cot.parquet | |
| - data_folder: '' | |
| data_type: parquet | |
| path: /pfs/training-data/kaichenzhang/data/VideoTool/longvideo_reason_sft_no_precomputed.parquet | |
| - data_folder: '' | |
| data_type: parquet | |
| path: /pfs/training-data/zuhaoyang/data/train/Video-R1-data/Video-R1-COT-165k.parquet | |
| - data_folder: '' | |
| data_type: parquet | |
| path: /pfs/training-data/kaichenzhang/data/VideoTool/tvg_charades_cot_no_precomputed.parquet | |