Sentence Similarity
sentence-transformers
Safetensors
Japanese
llama
feature-extraction
dense
Generated from Trainer
dataset_size:12451
loss:MultipleNegativesRankingLoss
Eval Results (legacy)
text-embeddings-inference
Instructions to use kushalc1/sarashina-embedding-v2-1b-jsts with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use kushalc1/sarashina-embedding-v2-1b-jsts with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("kushalc1/sarashina-embedding-v2-1b-jsts") sentences = [ "草原で2頭のシマウマが草を食べています。", "芝の上に5体象のオブジェが置いてあります。", "テーブルトップが大理石になってる台所です。", "草地にシマウマが二頭並んで草を食べています。" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
| { | |
| "word_embedding_dimension": 1792, | |
| "pooling_mode_cls_token": false, | |
| "pooling_mode_mean_tokens": false, | |
| "pooling_mode_max_tokens": false, | |
| "pooling_mode_mean_sqrt_len_tokens": false, | |
| "pooling_mode_weightedmean_tokens": false, | |
| "pooling_mode_lasttoken": true, | |
| "include_prompt": false | |
| } |