Feature Extraction
Transformers
English
qwen2_5_omni_thinker
text-generation
multimodal-embedding
any-to-any-retrieval
text-image-retrieval
video-retrieval
audio-retrieval
qwen2.5-omni
Instructions to use Sony/OmniUE-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Sony/OmniUE-3B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Sony/OmniUE-3B")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Sony/OmniUE-3B") model = AutoModelForSeq2SeqLM.from_pretrained("Sony/OmniUE-3B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download adapter_model.bin from Sony/OmniUE-3B: direct link, hf CLI and curl.
- Browser
- Download file 182 MB
-
https://huggingface.co/Sony/OmniUE-3B/resolve/main/adapter_model.bin
- Command line
-
hf download hf://Sony/OmniUE-3B/adapter_model.bin
-
curl -L -o adapter_model.bin https://huggingface.co/Sony/OmniUE-3B/resolve/main/adapter_model.bin
182 MB
- Xet hash:
- 927d5909aa31dd7d7863148b4b08e03c8662f637777680ae5a2b8d75068da836
- Size of remote file:
- 182 MB
- SHA256:
- e4241cc1bca8d0bac3b1dd8fd86ff88c22ac2556a34ace9834c897fc5198b874
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.