SentenceTransformer based on neuralmind/bert-large-portuguese-cased

This is a sentence-transformers model finetuned from neuralmind/bert-large-portuguese-cased. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: neuralmind/bert-large-portuguese-cased
Maximum Sequence Length: 512 tokens
Output Dimensionality: 1024 dimensions
Similarity Function: Cosine Similarity

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False, 'architecture': '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})
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("sentence_transformers_model_id")
# Run inference
sentences = [
            "o autor possuía..., ",
            "a parte autora é servidor pública...",
            "a parte autora é..."
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 1.0000, 0.8019],
#         [1.0000, 1.0000, 0.8019],
#         [0.8019, 0.8019, 1.0000]])

Evaluation

Metrics

Semantic Similarity

Dataset: sts-dev-dot
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_dot	0.1879
spearman_dot	0.1733

Semantic Similarity

Dataset: sts-dev-euclidian
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_euclidean	0.6901
spearman_euclidean	0.6918

Semantic Similarity

Dataset: sts-dev-manhattan
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_manhattan	0.6894
spearman_manhattan	0.6915

Semantic Similarity

Dataset: sts-dev-cosine
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.6698
spearman_cosine	0.6928

Semantic Similarity

Dataset: sts-dev-dot
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_dot	0.1879
spearman_dot	0.1733

Semantic Similarity

Dataset: sts-dev-euclidian
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_euclidean	0.6901
spearman_euclidean	0.6918

Semantic Similarity

Dataset: sts-dev-manhattan
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_manhattan	0.6894
spearman_manhattan	0.6915

Semantic Similarity

Dataset: sts-dev-cosine
Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.6698
spearman_cosine	0.6928

Training Details

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
learning_rate: 1e-05
num_train_epochs: 4
warmup_ratio: 0.1
fp16: True
resume_from_checkpoint: True

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 16
per_device_eval_batch_size: 16
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_steps: None
torch_empty_cache_steps: None
learning_rate: 1e-05
weight_decay: 0.0
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 4
max_steps: -1
lr_scheduler_type: linear
lr_scheduler_kwargs: {}
warmup_ratio: 0.1
warmup_steps: 0
log_level: passive
log_level_replica: warning
log_on_each_node: True
logging_nan_inf_filter: True
save_safetensors: True
save_on_each_node: False
save_only_model: False
restore_callback_states_from_checkpoint: False
no_cuda: False
use_cpu: False
use_mps_device: False
seed: 42
data_seed: None
jit_mode_eval: False
use_ipex: False
bf16: False
fp16: True
fp16_opt_level: O1
half_precision_backend: auto
bf16_full_eval: False
fp16_full_eval: False
tf32: None
local_rank: 0
ddp_backend: None
tpu_num_cores: None
tpu_metrics_debug: False
debug: []
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_prefetch_factor: None
past_index: -1
disable_tqdm: False
remove_unused_columns: True
label_names: None
load_best_model_at_end: False
ignore_data_skip: False
fsdp: []
fsdp_min_num_params: 0
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
fsdp_transformer_layer_cls_to_wrap: None
accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
deepspeed: None
label_smoothing_factor: 0.0
optim: adamw_torch
optim_args: None
adafactor: False
group_by_length: False
length_column_name: length
ddp_find_unused_parameters: None
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
dataloader_pin_memory: True
dataloader_persistent_workers: False
skip_memory_metrics: True
use_legacy_prediction_loop: False
push_to_hub: False
resume_from_checkpoint: True
hub_model_id: None
hub_strategy: every_save
hub_private_repo: None
hub_always_push: False
hub_revision: None
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
include_for_metrics: []
eval_do_concat_batches: True
fp16_backend: auto
push_to_hub_model_id: None
push_to_hub_organization: None
mp_parameters:
auto_find_batch_size: False
full_determinism: False
torchdynamo: None
ray_scope: last
ddp_timeout: 1800
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
include_tokens_per_second: False
include_num_input_tokens_seen: False
neftune_noise_alpha: None
optim_target_modules: None
batch_eval_metrics: False
eval_on_start: False
use_liger_kernel: False
liger_kernel_config: None
eval_use_gather_object: False
average_tokens_across_devices: False
prompts: None
batch_sampler: batch_sampler
multi_dataset_batch_sampler: proportional
router_mapping: {}
learning_rate_mapping: {}

Framework Versions

Python: 3.10.12
Sentence Transformers: 5.0.0
Transformers: 4.53.3
PyTorch: 2.7.1+cu126
Accelerate: 1.9.0
Datasets: 3.6.0
Tokenizers: 0.21.2

Authors

Diretoria de Inteligência Artificial, Ciência de Dados e Estatística do Tribunal de Justiça do Estado de Goiás (TJGO).

Citation

BibTeX

LexIris-pt / LexBert-pt

@inproceedings{santos-etal-2026-lexiris,
    title = "{L}ex{I}ris-pt and {L}ex{B}ert-pt: Specialized Sentence Embeddings for Legal Similarity in {B}razilian {P}ortuguese",
    author = "Santos, Willgnner Ferreira  and
      Viana, Jo{\~a}o Gabriel Grandotto  and
      J{\'u}nior, Ant{\^o}nio Pires de Castro  and
      Trindade, Fernando Ribeiro  and
      Silva, N{\'a}dia F{\'e}lix Felipe da",
    editor = "Souza, Marlo  and
      de-Dios-Flores, Iria  and
      Santos, Diana  and
      Freitas, Larissa  and
      Souza, Jackson Wilke da Cruz  and
      Ribeiro, Eug{\'e}nio",
    booktitle = "Proceedings of the 17th International Conference on Computational Processing of {P}ortuguese ({PROPOR} 2026) - Vol. 1",
    month = apr,
    year = "2026",
    address = "Salvador, Brazil",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.propor-1.53/",
    pages = "540--550",
    ISBN = "979-8-89176-387-6",
    abstract = "This work presents and evaluates two specialized sentence embedding models for the Portuguese legal domain, LexIris-pt and LexBert-pt, obtained through supervised fine-tuning of BERT-based models using pairs of initial petitions. We propose a comparative evaluation protocol along three fronts: (i) zero-shot inference with pretrained embeddings, (ii) supervised fine-tuning on these pairs, and (iii) vector retrieval with incremental clustering over a corpus of 20,000 initial petitions. The results show that fine-tuning consistently increases correlations with reference scores and improves performance in vector retrieval; additionally, the vector retrieval stage indicates that the metric configured in the index (cosine similarity or inner product) can change the granularity of the partitioning under a fixed threshold, reinforcing the need for joint calibration among the encoder, metric and threshold. After auditing by specialists from the partner institution, LexIris-pt and LexBert-pt were operationally adopted to support the screening and organization of repetitive claims and predatory litigation."
}

Sentence Transformers

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

BERTIMBAU

@inproceedings{souza2020bertimbau,
  author    = {F{\'a}bio Souza and
               Rodrigo Nogueira and
               Roberto Lotufo},
  title     = {{BERT}imbau: pretrained {BERT} models for {B}razilian {P}ortuguese},
  booktitle = {9th Brazilian Conference on Intelligent Systems, {BRACIS}, Rio Grande do Sul, Brazil, October 20-23 (to appear)},
  year      = {2020}
}

Downloads last month: 18

Safetensors

Model size

0.3B params

Tensor type

F32

Model tree for DIACDE/bertimbaularge_tjgo_diacde_sts

Base model

neuralmind/bert-large-portuguese-cased

Finetuned

(61)

this model

Paper for DIACDE/bertimbaularge_tjgo_diacde_sts

Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

Paper • 1908.10084 • Published Aug 27, 2019 • 13

Evaluation results

Pearson Dot on sts dev dot
self-reported

0.188
Spearman Dot on sts dev dot
self-reported

0.173
Pearson Dot on sts dev dot
self-reported

0.188
Spearman Dot on sts dev dot
self-reported

0.173
Pearson Euclidean on sts dev euclidian
self-reported

0.690
Spearman Euclidean on sts dev euclidian
self-reported

0.692
Pearson Euclidean on sts dev euclidian
self-reported

0.690
Spearman Euclidean on sts dev euclidian
self-reported

0.692
Pearson Manhattan on sts dev manhattan
self-reported

0.689
Spearman Manhattan on sts dev manhattan
self-reported

0.692
Pearson Manhattan on sts dev manhattan
self-reported

0.689
Spearman Manhattan on sts dev manhattan
self-reported

0.692
Pearson Cosine on sts dev cosine
self-reported

0.670
Spearman Cosine on sts dev cosine
self-reported

0.693
Pearson Cosine on sts dev cosine
self-reported

0.670
Spearman Cosine on sts dev cosine
self-reported

0.693