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 1_Pooling/config.json from Futyn-Maker/ruscxn-embedder: direct link, hf CLI and curl.
- Browser
- Download file 297 Bytes
-
https://huggingface.co/Futyn-Maker/ruscxn-embedder/resolve/main/1_Pooling/config.json
- Command line
-
hf download hf://Futyn-Maker/ruscxn-embedder/1_Pooling/config.json
-
curl -L -o config.json https://huggingface.co/Futyn-Maker/ruscxn-embedder/resolve/main/1_Pooling/config.json
297 Bytes
| { | |
| "word_embedding_dimension": 1024, | |
| "pooling_mode_cls_token": false, | |
| "pooling_mode_mean_tokens": true, | |
| "pooling_mode_max_tokens": false, | |
| "pooling_mode_mean_sqrt_len_tokens": false, | |
| "pooling_mode_weightedmean_tokens": false, | |
| "pooling_mode_lasttoken": false, | |
| "include_prompt": true | |
| } |