Video-Text-to-Text
Transformers
Safetensors
English
videochat_flash_qwen
feature-extraction
multimodal
custom_code
Eval Results (legacy)
Instructions to use OpenGVLab/VideoChat-Flash-Qwen2_5-2B_res448 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenGVLab/VideoChat-Flash-Qwen2_5-2B_res448 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("OpenGVLab/VideoChat-Flash-Qwen2_5-2B_res448", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
RuntimeError: shape '[-1, 0]' is invalid for input of size 1206
#1
by 2U1 - opened
It keeps throwing me an error of RuntimeError: shape '[-1, 0]' is invalid for input of size 1206 in the video inference.
The last size changes but the same error occurs every time.
You need to install transformers==4.40.1, I modify the qwen2 of this version.