Visual Question Answering
Transformers
English
videorefer_qwen2
text-generation
multimodal large language model
large video-language model
Instructions to use DAMO-NLP-SG/VideoRefer-7B-stage2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DAMO-NLP-SG/VideoRefer-7B-stage2 with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "visual-question-answering" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("visual-question-answering", model="DAMO-NLP-SG/VideoRefer-7B-stage2")# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("DAMO-NLP-SG/VideoRefer-7B-stage2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download region_encoder.bin from DAMO-NLP-SG/VideoRefer-7B-stage2: direct link, hf CLI and curl.
- Browser
- Download file 34 MB
-
https://huggingface.co/DAMO-NLP-SG/VideoRefer-7B-stage2/resolve/main/region_encoder.bin
- Command line
-
hf download hf://DAMO-NLP-SG/VideoRefer-7B-stage2/region_encoder.bin
-
curl -L -o region_encoder.bin https://huggingface.co/DAMO-NLP-SG/VideoRefer-7B-stage2/resolve/main/region_encoder.bin
34 MB
- Xet hash:
- 3155d36899f42726cfc1bb64ae3426ab95a080701a1154820c3188563bd7253c
- Size of remote file:
- 34 MB
- SHA256:
- 135413a5f03d42f6baf1282a20463c6559ebe5df89311556afeeca730727de27
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.