Sentence Similarity
sentence-transformers
Safetensors
Russian
feature-extraction
static-embeddings
binary
russian
8-bit precision
Instructions to use BorisTM/starse with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use BorisTM/starse with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("BorisTM/starse") sentences = [ "Это счастливый человек", "Это счастливая собака", "Это очень счастливый человек", "Сегодня солнечный день" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
| { | |
| "repo_id": "BorisTM/starse-512", | |
| "model": "StaRSE-512", | |
| "dim": 512, | |
| "vocab_size": 120138, | |
| "encoding": "packed_sign_bits_with_per_token_l2_norm", | |
| "weights_layout": { | |
| "packed_signs": [ | |
| 120138, | |
| 64 | |
| ], | |
| "norms": [ | |
| 120138 | |
| ] | |
| }, | |
| "source_checkpoint": "starse-512 + 10000 joint qaware STE continuation (cultura_ru_only_45m, sw=0 bw=0.173 tkl=1.14 lr=3.77e-3 scale=20 mode=current cube=1.07e-4 up=7.89e-4)", | |
| "packed_at_utc": "2026-05-23T09:27:12Z", | |
| "rumteb_binary": 0.5116301998770688, | |
| "rumteb_soft": 0.5056 | |
| } | |