Video-Text-to-Text
Transformers
Safetensors
qwen3_vl
image-text-to-text
video
temporal-grounding
qwen3-vl
Eval Results
Instructions to use MCG-NJU/TimeLens2-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MCG-NJU/TimeLens2-8B with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("MCG-NJU/TimeLens2-8B") model = AutoModelForMultimodalLM.from_pretrained("MCG-NJU/TimeLens2-8B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add OmniCompass evaluation results
#2
by VCLab-PolyU - opened
Add the OmniCompass benchmark authors' published results for TimeLens2-8B on omnicompass_vl. Each value is Overall Cross-Specification Consistency Score on a 0-100 scale; higher is better.
Source: https://omnicompass.netlify.app/#leaderboard
Benchmark: https://huggingface.co/datasets/VCLab-PolyU/OmniCompass
The YAML preserves the published one-decimal scores and records frame counts and source attribution. It adds evaluation metadata only and makes no HF verified claim.
ZhuYuhan changed pull request status to merged