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:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("OpenGVLab/VideoChat-Flash-Qwen2_5-2B_res448", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
IndexError: too many indices for tensor of dimension 2
#2
by zhxy - opened
huggingface/modules/transformers_modules/OpenGVLab/VideoChat-Flash-Qwen2_5-2B_res448/ee222dcf618c9fd85e85ddc76340ec84894806b9/modeling_qwen2_flash.py", line 1231, in
features = [cur_features[cur_attention_mask] for cur_features, cur_attention_mask in zip(features, attention_mask)]
Have you use the transformers==4.40.1?
updating python to 3.11, it works, thanks
zhxy changed discussion status to closed
