Sentence Similarity
sentence-transformers
Safetensors
Russian
xlm-roberta
feature-extraction
Generated from Trainer
dataset_size:15298
loss:CachedMultipleNegativesSymmetricRankingLoss
russian
constructicon
nlp
linguistics
text-embeddings-inference
Instructions to use Futyn-Maker/ruscxn-embedder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Futyn-Maker/ruscxn-embedder with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Futyn-Maker/ruscxn-embedder") sentences = [ "Instruct: Given a sentence, find the constructions of the Russian Constructicon that it contains\nQuery: Петр так и замер.", "NP-Nom так и VP-Pfv", "VP вокруг да около", "NP-Nom в гробу видать NP-Acc" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from Futyn-Maker/ruscxn-embedder: direct link, hf CLI and curl.
- Browser
- Download file 17.1 MB
-
https://huggingface.co/Futyn-Maker/ruscxn-embedder/resolve/main/tokenizer.json
- Command line
-
hf download hf://Futyn-Maker/ruscxn-embedder/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/Futyn-Maker/ruscxn-embedder/resolve/main/tokenizer.json
17.1 MB
- Xet hash:
- 900d575674d5bfcd5c2b9059c9221a42f92c957ed7230f7e096d3e9580c3e4c2
- Size of remote file:
- 17.1 MB
- SHA256:
- 883b037111086fd4dfebbbc9b7cee11e1517b5e0c0514879478661440f137085
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.