Sentence Similarity
sentence-transformers
Safetensors
Japanese
English
qwen3
feature-extraction
mteb
japanese
retrieval
text-embeddings-inference
Instructions to use sionic-ai/comsat-embed-ja-8b-preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use sionic-ai/comsat-embed-ja-8b-preview with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("sionic-ai/comsat-embed-ja-8b-preview") 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] - Notebooks
- Google Colab
- Kaggle
Download model.safetensors from sionic-ai/comsat-embed-ja-8b-preview: direct link, hf CLI and curl.
- Browser
- Download file 15.1 GB
-
https://huggingface.co/sionic-ai/comsat-embed-ja-8b-preview/resolve/main/model.safetensors
- Command line
-
hf download hf://sionic-ai/comsat-embed-ja-8b-preview/model.safetensors
-
curl -L -o model.safetensors https://huggingface.co/sionic-ai/comsat-embed-ja-8b-preview/resolve/main/model.safetensors
15.1 GB
- Xet hash:
- 8e73c69fa83629363c9995f890cdc30427728292d23e8ab23560baa3863e9397
- Size of remote file:
- 15.1 GB
- SHA256:
- 330d60880ae7c85adef285aa103a65ef2ec952894ebbb4a59509dc2f0b056a6e
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.