Video-Text-to-Text
Transformers
Safetensors
llava_onevision
image-text-to-text
multimodal
multilingual
vlm
translation
Instructions to use utter-project/TowerVideo-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use utter-project/TowerVideo-2B with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("utter-project/TowerVideo-2B") model = AutoModelForMultimodalLM.from_pretrained("utter-project/TowerVideo-2B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from utter-project/TowerVideo-2B: direct link, hf CLI and curl.
- Browser
- Download file 34.4 MB
-
https://huggingface.co/utter-project/TowerVideo-2B/resolve/main/tokenizer.json
- Command line
-
hf download hf://utter-project/TowerVideo-2B/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/utter-project/TowerVideo-2B/resolve/main/tokenizer.json
34.4 MB
- Xet hash:
- 7c71542357fd4dd2de528213ae997b57460dee2a7e19eb87f34509749d5e1d43
- Size of remote file:
- 34.4 MB
- SHA256:
- 78101460bab7a4da527d424562e7b90b2e55252a4f6b17231a51d588e06235e0
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.