Serafim 335m Portuguese (PT) Sentence Encoder tuned for Information Retrieval (IR)

This is a sentence-transformers model: It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search.

Usage (Sentence-Transformers)

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

pip install -U sentence-transformers

Then you can use the model like this:

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

model = SentenceTransformer('PORTULAN/serafim-335m-portuguese-pt-sentence-encoder-ir')
embeddings = model.encode(sentences)
print(embeddings)

Usage (HuggingFace Transformers)

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('PORTULAN/serafim-335m-portuguese-pt-sentence-encoder-ir')
model = AutoModel.from_pretrained('PORTULAN/serafim-335m-portuguese-pt-sentence-encoder-ir')

# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')

# Compute token embeddings
with torch.no_grad():
    model_output = model(**encoded_input)

# Perform pooling. In this case, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])

print("Sentence embeddings:")
print(sentence_embeddings)

Evaluation Results

For an automated evaluation of this model, see the Sentence Embeddings Benchmark: https://seb.sbert.net

Training

The model was trained with the parameters:

DataLoader:

sentence_transformers.datasets.NoDuplicatesDataLoader.NoDuplicatesDataLoader of length 936019 with parameters:

{'batch_size': 85}

Loss:

sentence_transformers.losses.GISTEmbedLoss.GISTEmbedLoss with parameters:

{'guide': SentenceTransformer(
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
(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, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
), 'temperature': 0.01}

Parameters of the fit()-Method:

{
    "epochs": 1,
    "evaluation_steps": 9361,
    "evaluator": "sentence_transformers.evaluation.InformationRetrievalEvaluator.InformationRetrievalEvaluator",
    "max_grad_norm": 1,
    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
    "optimizer_params": {
        "lr": 1e-05
    },
    "scheduler": "WarmupLinear",
    "steps_per_epoch": 936019,
    "warmup_steps": 93602,
    "weight_decay": 0.01
}

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'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})
)

Citing & Authors

The article has been presented at EPIA 2024 conference and published by Springer:

@InProceedings{epia2024serafim,
    title={Open Sentence Embeddings for Portuguese with the Serafim PT* encoders family}, 
    author={Luís Gomes and António Branco and João Silva and João Rodrigues and Rodrigo Santos},
    editor={Manuel Filipe Santos and José Machado and Paulo Novais and Paulo Cortez and Pedro Miguel Moreira},
    booktitle={Progress in Artificial Intelligence},
    doi={doi.org/10.1007/978-3-031-73503-5_22},
    year={2024},
    publisher={Springer Nature Switzerland},
    address={Cham},
    pages={267--279},
    isbn={978-3-031-73503-5}
}

Before publication by Springer, the pre-print was available at arXiv:

@misc{gomes2024opensentenceembeddingsportuguese,
    title={Open Sentence Embeddings for Portuguese with the Serafim PT* encoders family}, 
    author={Luís Gomes and António Branco and João Silva and João Rodrigues and Rodrigo Santos},
    year={2024},
    eprint={2407.19527},
    archivePrefix={arXiv},
    primaryClass={cs.CL},
    url={https://arxiv.org/abs/2407.19527}, 
}