Feature Extraction
Transformers
Safetensors
English
qwen2_vl
image-text-to-text
multimodal
video embedding
ncsoft
ncai
varco
Instructions to use NCSOFT/GME-VARCO-VISION-Embedding with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NCSOFT/GME-VARCO-VISION-Embedding with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="NCSOFT/GME-VARCO-VISION-Embedding")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("NCSOFT/GME-VARCO-VISION-Embedding") model = AutoModelForMultimodalLM.from_pretrained("NCSOFT/GME-VARCO-VISION-Embedding") - Notebooks
- Google Colab
- Kaggle
Need to define tokenizer and process_vision_info helper in demo code
#1
by deleted - opened
Hi! Thanks for your comment.
We've just updated the README to better guide you in using GME-VARCO-VISION-Embedding. Please remember to install qwen_vl_utils beforehand, as we utilize process_vision_info from that package.
deleted changed discussion status to closed