Video-Text-to-Text
Transformers
Safetensors
qwen3_5
image-text-to-text
SAVER
video
video-question-answering
temporal-grounding
reinforcement-learning
Instructions to use lmsdss/SAVER-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lmsdss/SAVER-2B with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("lmsdss/SAVER-2B") model = AutoModelForMultimodalLM.from_pretrained("lmsdss/SAVER-2B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from lmsdss/SAVER-2B: direct link, hf CLI and curl.
- Browser
- Download file 20 MB
-
https://huggingface.co/lmsdss/SAVER-2B/resolve/refs%2Fpr%2F1/tokenizer.json
- Command line
-
hf download hf://lmsdss/SAVER-2B@refs/pr/1/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/lmsdss/SAVER-2B/resolve/refs%2Fpr%2F1/tokenizer.json
20 MB
- Xet hash:
- 458bcbf483ed805b4297af928f717e64bd00c633a07be5fae5717cacbd48e2ef
- Size of remote file:
- 20 MB
- SHA256:
- 87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.