Video-Text-to-Text
Transformers
Safetensors
English
qwen2_5_vl
video-scene-graph
scene-graph-generation
video-understanding
trajectory-aware
perceiver-resampler
qwen2.5-vl
text-generation-inference
Instructions to use UWGZQ/TRASER with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use UWGZQ/TRASER with Transformers:
# Load model directly from transformers import AutoProcessor, Qwen2_5_VLForConditionalGeneration_Insert processor = AutoProcessor.from_pretrained("UWGZQ/TRASER") model = Qwen2_5_VLForConditionalGeneration_Insert.from_pretrained("UWGZQ/TRASER") - Notebooks
- Google Colab
- Kaggle
lm_head.weight missing from checkpoint and inference returns garbage on the bundled example
1
#2 opened about 1 month ago
by
jishnu-jp