CoolFace
Modelpublic

victormuryn/use-generated-pt

sourceHugging Faceapache-2.0updated 22d agoView on Hugging Face
0likes42downloads
Model Card

use-generated-pt

This model is a fine-tuned version of paraphrase-multilingual-mpnet-base-v2, trained on the Ukrainian text corpus UberText 2.0 with generated augmentation with pool targets. It is part of the Ukrainian Sentence Embeddings collection, which explores the effect of different training strategies on sentence embedding quality for Ukrainian.

Model Description

The model was fine-tuned using a contrastive objective on UberText 2.0, generated augmentation.

Collection Overview

ModelDescription
use-natural-no-ptRaw UberText 2.0, no augmentation, no pool targets
use-natural-ptRaw UberText 2.0, no augmentation, pool targets
use-generated-no-ptGenerated augmentation, no pool targets
use-generated-ptGenerated augmentation, pool targets
use-translation-no-ptBack-translation augmentation, no pool targets
use-translation-ptBack-translation augmentation, pool targets
use-mask-no-ptMasking augmentation, no pool targets
use-mask-ptMasking augmentation, pool targets
use-dropout-no-ptDropout augmentation, no pool targets
use-dropout-ptDropout augmentation, pool targets
use-token-shuffle-no-ptToken-shuffling augmentation, no pool targets
use-token-shuffle-ptToken-shuffling augmentation, pool targets
use-combined-no-ptCombined augmentation strategies, no pool targets
use-combined-ptCombined augmentation strategies, pool targets
use-stochastic-no-ptMarkov-based stochastic augmentation, no pool targets
use-stochastic-ptMarkov-based stochastic augmentation, pool targets

Usage

python
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("victormuryn/use-generated-pt")
sentences = [
    "Проводжає сина мати захищати рідний край",
    "Хоч би малесеньку хатину він мріяв мати над Дніпром",
]
embeddings = model.encode(sentences)
print(embeddings.shape)

Training Details

  • —Base model: paraphrase-multilingual-mpnet-base-v2
  • —Training corpus: UberText 2.0
  • —Augmentation: Generated
  • —Pool targets: Yes

Citation

To be added

License

Apache 2.0