Image Feature Extraction
Transformers
Safetensors
qwen3_vl
multimodal
vision-language
embeddings
image-retrieval
visual-grounding
Instructions to use fushh7/ObjEmbed-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use fushh7/ObjEmbed-2B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="fushh7/ObjEmbed-2B")# Load model directly from transformers import AutoProcessor, WeDetectEmbedding processor = AutoProcessor.from_pretrained("fushh7/ObjEmbed-2B") model = WeDetectEmbedding.from_pretrained("fushh7/ObjEmbed-2B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from fushh7/ObjEmbed-2B: direct link, hf CLI and curl.
- Browser
- Download file 11.4 MB
-
https://huggingface.co/fushh7/ObjEmbed-2B/resolve/main/tokenizer.json
- Command line
-
hf download hf://fushh7/ObjEmbed-2B/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/fushh7/ObjEmbed-2B/resolve/main/tokenizer.json
11.4 MB
- Xet hash:
- 93b66007d1fe2b426b11c0a2b59db149421b584096333305f94fb4c206b46880
- Size of remote file:
- 11.4 MB
- SHA256:
- 987b88e8d99aeee051cddd7e8191e22230510bb421f273a1294488b3111ac0c0
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.