Feature Extraction
Transformers
Safetensors
qwen3_5
image-text-to-text
multimodal
text
image
video
visual-document
embedding
retrieval
Instructions to use ATH-MaaS/Ovis-VL-Embedding-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ATH-MaaS/Ovis-VL-Embedding-9B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="ATH-MaaS/Ovis-VL-Embedding-9B")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("ATH-MaaS/Ovis-VL-Embedding-9B") model = AutoModelForMultimodalLM.from_pretrained("ATH-MaaS/Ovis-VL-Embedding-9B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download model/args.json from ATH-MaaS/Ovis-VL-Embedding-9B: direct link, hf CLI and curl.
- Browser
- Download file 86 Bytes
-
https://huggingface.co/ATH-MaaS/Ovis-VL-Embedding-9B/resolve/main/model/args.json
- Command line
-
hf download hf://ATH-MaaS/Ovis-VL-Embedding-9B/model/args.json
-
curl -L -o args.json https://huggingface.co/ATH-MaaS/Ovis-VL-Embedding-9B/resolve/main/model/args.json
86 Bytes
| { | |
| "model_type": "qwen3_5", | |
| "task_type": "embedding", | |
| "template": "qwen3_5_emb" | |
| } |