Instructions to use LCO-Embedding/LCO-Embedding-Omni-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use LCO-Embedding/LCO-Embedding-Omni-7B with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("LCO-Embedding/LCO-Embedding-Omni-7B") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Transformers
How to use LCO-Embedding/LCO-Embedding-Omni-7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="LCO-Embedding/LCO-Embedding-Omni-7B")# Load model directly from transformers import AutoTokenizer, AutoModelForImageTextToText tokenizer = AutoTokenizer.from_pretrained("LCO-Embedding/LCO-Embedding-Omni-7B") model = AutoModelForImageTextToText.from_pretrained("LCO-Embedding/LCO-Embedding-Omni-7B") - Notebooks
- Google Colab
- Kaggle
Integrate with Sentence Transformers v5.4
Hello!
Pull Request overview
- Integrate this model as a Sentence Transformers
SentenceTransformer(targeting v5.4)
Details
This is the sibling PR to https://huggingface.co/LCO-Embedding/LCO-Embedding-Omni-3B/discussions/1.
I see that this README also has some audio/video examples. Perhaps I can include those as well in the Sentence Transformers portion, although it's likely preferable to add working examples using some remote audio to load. For longer video, we can also set e.g. fps/max pixels, etc. akin to https://huggingface.co/nvidia/omni-embed-nemotron-3b#using-sentence-transformers
Let me know if you have any questions, etc.!
- Tom Aarsen
Thanks again! Merging this as well. I can work on adding audio/video examples for the Sentence Transformers portion tmr; thanks for pointing to the video examples in omni embed nemotron!
Chenghao