Sentence Similarity
sentence-transformers
Safetensors
Russian
xlm-roberta
feature-extraction
Generated from Trainer
dataset_size:904
loss:MatryoshkaLoss
loss:MultipleNegativesRankingLoss
Eval Results (legacy)
text-embeddings-inference
Instructions to use fitlemon/bge-m3-ru-ostap with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use fitlemon/bge-m3-ru-ostap with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("fitlemon/bge-m3-ru-ostap") sentences = [ "Какой у тебя план на будущее?", "Работа — это скучно, если не считать, что Уголовный розыск считает меня своим работником.", "Я дам вам парабеллум, если дружба станет слишком серьезной!", "План? Из Васюков полетят сигналы на Марс, а я буду на Земле собирать деньги на билет." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from fitlemon/bge-m3-ru-ostap: direct link, hf CLI and curl.
- Browser
- Download file 17.1 MB
-
https://huggingface.co/fitlemon/bge-m3-ru-ostap/resolve/main/tokenizer.json
- Command line
-
hf download hf://fitlemon/bge-m3-ru-ostap/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/fitlemon/bge-m3-ru-ostap/resolve/main/tokenizer.json
17.1 MB
- Xet hash:
- 5d747ca97fe6e145aef974d51b6921c06a4eed57a0513eb2427235a9af134752
- Size of remote file:
- 17.1 MB
- SHA256:
- e4f7e21bec3fb0044ca0bb2d50eb5d4d8c596273c422baef84466d2c73748b9c
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.