🚀 stsb-xlm-r-multilingual-ro

This is a sentence-transformers model that maps sentences & paragraphs to a 768-dimensional dense vector space. It can be used for tasks such as clustering or semantic search. It is a fine-tuned version of stsb-xlm-r-multilingual for the Romanian language.

🚀 Quick Start

✨ Features

• Maps sentences and paragraphs to a 768-dimensional dense vector space.
• Suitable for tasks like clustering and semantic search.
• Fine-tuned for the Romanian language.

📦 Installation

Using this model becomes easy when you have sentence-transformers installed:

pip install -U sentence-transformers

💻 Usage Examples

Basic Usage

from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]

model = SentenceTransformer('BlackKakapo/stsb-xlm-r-multilingual-ro')
embeddings = model.encode(sentences)
print(embeddings)

Advanced Usage

Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.

from transformers import AutoTokenizer, AutoModel
import torch


#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)


# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']

# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('BlackKakapo/stsb-xlm-r-multilingual-ro')
model = AutoModel.from_pretrained('BlackKakapo/stsb-xlm-r-multilingual-ro')

📚 Documentation

Training

DataSet: STS-ro The text dataset is in Romanian (ro). Score is from 0 to 5, that's why I divide score by 5, because the score for EmbeddingSimilarityEvaluator (evaluator for finetune) needs to be from 0 to 1. Dataset Structure:

{
'score': 1.5,
 'sentence1': 'Un bărbat cântă la harpă.',
 'sentence2': 'Un bărbat cântă la claviatură.',
}

DataLoader: torch.utils.data.dataloader.DataLoader of length 223 with parameters:

{'batch_size': 32, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}

Loss: sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss

Parameters of the fit()-Method:

{
    "epochs": 10,
    "evaluation_steps": 0,
    "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
    "max_grad_norm": 1,
    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
    "optimizer_params": {
        "lr": 2e-05
    },
    "scheduler": "WarmupLinear",
    "steps_per_epoch": null,
    "warmup_steps": 100,
    "weight_decay": 0.01
}

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: XLMRobertaModel 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)

Citing & Authors

BlackKakapo

📄 License

No license information provided in the original document, so this section is skipped.

🔧 Technical Details

No additional technical details provided in the original document, so this section is skipped.