Video-Text-to-Text
Transformers
Safetensors
English
qwen2_5_vl
image-text-to-text
video-grounding
temporal-grounding
video-understanding
qwen2-vl
text-generation-inference
Instructions to use TencentARC/TimeLens-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TencentARC/TimeLens-7B with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("TencentARC/TimeLens-7B") model = AutoModelForMultimodalLM.from_pretrained("TencentARC/TimeLens-7B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
File size: 133 Bytes
3c8f7cb | 1 2 3 4 | version https://git-lfs.github.com/spec/v1
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
size 11421896
|