Video-Text-to-Text
Transformers
Safetensors
English
qwen3_vl
image-text-to-text
video-grounding
temporal-grounding
video-understanding
qwen3-vl
Eval Results
Instructions to use TencentARC/TimeLens-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TencentARC/TimeLens-8B with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("TencentARC/TimeLens-8B") model = AutoModelForMultimodalLM.from_pretrained("TencentARC/TimeLens-8B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add OmniCompass evaluation results
#3
by VCLab-PolyU - opened
.eval_results/omnicompass.yaml
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
- dataset:
|
| 2 |
+
id: VCLab-PolyU/OmniCompass
|
| 3 |
+
task_id: OmniCompass-VL
|
| 4 |
+
value: 23.6
|
| 5 |
+
source:
|
| 6 |
+
url: https://omnicompass.netlify.app/#leaderboard
|
| 7 |
+
name: OmniCompass official results
|
| 8 |
+
user: VCLab-PolyU
|
| 9 |
+
notes: OmniCompass-VL; Overall CS on a 0-100 scale, higher is better. 32 video frames;
|
| 10 |
+
paired Text and Text+Image; TG, SG and QA. Imported from the benchmark authors'
|
| 11 |
+
published results, rounded to one decimal. Evaluation settings and model-specific
|
| 12 |
+
limits follow the cited source. This submission does not claim HF verified status.
|