mrm8488/modernbert-embed-base-ft-sts-spanish-matryoshka-768-64

SentenceTransformer based on nomic-ai/modernbert-embed-base

This is a sentence-transformers model finetuned from nomic-ai/modernbert-embed-base on the stsbmulties_augmented (private) dataset. It maps sentences & paragraphs to a 768-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: nomic-ai/modernbert-embed-base <!-- at revision bb0033c9f3def40c3c5b26ff0b53c74f3320d703 -->
• —Maximum Sequence Length: 8192 tokens
• —Output Dimensionality: 768 dimensions
• —Similarity Function: Cosine Similarity
• —Training Dataset:
• —Private stsb dataset

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': 8192, 'do_lower_case': False}) with Transformer model: ModernBertModel 
  (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})
  (2): Normalize()
)

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("mrm8488/modernbert-embed-base-ft-sts-spanish-matryoshka-768-64-5e")
# Run inference
sentences = [
    'El cordero está mirando hacia la cámara.',
    'Un gato está mirando hacia la cámara también.',
    '"Sí, no deseo estar presente durante este testimonio", declaró tranquilamente Peterson, de 31 años, al juez cuando fue devuelto a su celda.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

<!--

Direct Usage (Transformers)

<details><summary>Click to see the direct usage in Transformers</summary>

</details> -->

<!--

Downstream Usage (Sentence Transformers)

You can finetune this model on your own dataset.

<details><summary>Click to expand</summary>

</details> -->

<!--

Out-of-Scope Use

List how the model may foreseeably be misused and address what users ought not to do with the model. -->

Evaluation

Metrics

Semantic Similarity

• —Datasets: sts-dev-768, sts-dev-512, sts-dev-256, sts-dev-128, sts-dev-64, sts-test-768, sts-test-512, sts-test-256, sts-test-128 and sts-test-64
• —Evaluated with <code>EmbeddingSimilarityEvaluator</code>

<!--

Bias, Risks and Limitations

What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model. -->

<!--

Recommendations

What are recommendations with respect to the foreseeable issues? For example, filtering explicit content. -->

Training Details

Training Dataset

stsbmulties_augmented (private)

• —Size: 2,697 training samples
• —Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
• —Approximate statistics based on the first 1000 samples: | | sentence1 | sentence2 | score | |:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:---------------------------------------------------------------| | type | string | string | float | | details | <ul><li>min: 9 tokens</li><li>mean: 28.42 tokens</li><li>max: 96 tokens</li></ul> | <ul><li>min: 10 tokens</li><li>mean: 28.01 tokens</li><li>max: 92 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 2.72</li><li>max: 5.0</li></ul> |
• —Samples: | sentence1 | sentence2 | score | |:------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------|:-------------------------------| | <code>El pájaro de tamaño reducido se posó con delicadeza en una rama cubierta de escarcha.</code> | <code>Un ave de color amarillo descansaba tranquilamente en una rama.</code> | <code>3.200000047683716</code> | | <code>Una chica está tocando la flauta en un parque.</code> | <code>Un grupo de músicos está tocando en un escenario al aire libre.</code> | <code>1.286</code> | | <code>La aclamada escritora británica, Doris Lessing, galardonada con el premio Nobel, fallece</code> | <code>La destacada autora británica, Doris Lessing, reconocida con el prestigioso Premio Nobel, muere</code> | <code>4.199999809265137</code> |
• —Loss: <code>MatryoshkaLoss</code> with these parameters:

  {
      "loss": "CoSENTLoss",
      "matryoshka_dims": [
          768,
          512,
          256,
          128,
          64
      ],
      "matryoshka_weights": [
          1,
          1,
          1,
          1,
          1
      ],
      "n_dims_per_step": -1
  }

Evaluation Dataset

stsbmulties_augmented (private)

• —Size: 697 evaluation samples
• —Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>score</code>
• —Approximate statistics based on the first 697 samples: | | sentence1 | sentence2 | score | |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:--------------------------------------------------------------| | type | string | string | float | | details | <ul><li>min: 9 tokens</li><li>mean: 29.35 tokens</li><li>max: 87 tokens</li></ul> | <ul><li>min: 9 tokens</li><li>mean: 28.52 tokens</li><li>max: 81 tokens</li></ul> | <ul><li>min: 0.0</li><li>mean: 2.3</li><li>max: 5.0</li></ul> |
• —Samples: | sentence1 | sentence2 | score | |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------| | <code>Un incendio ocurrido en un hospital psiquiátrico ruso resultó en la trágica muerte de 38 personas.</code> | <code>Se teme que el incendio en un hospital psiquiátrico ruso cause la pérdida de la vida de 38 individuos.</code> | <code>4.199999809265137</code> | | <code>"Street dijo que el otro individuo a veces se siente avergonzado de su fiesta, lo cual provoca risas en la multitud"</code> | <code>"A veces, el otro tipo se encuentra avergonzado de su fiesta y no se le puede culpar."</code> | <code>3.5</code> | | <code>El veterano diplomático de Malasia tuvo un encuentro con Suu Kyi el miércoles en la casa del lago en Yangon donde permanece bajo arresto domiciliario.</code> | <code>Razali Ismail tuvo una reunión de 90 minutos con Suu Kyi, quien ganó el Premio Nobel de la Paz en 1991, en su casa del lago donde está recluida.</code> | <code>3.691999912261963</code> |
• —Loss: <code>MatryoshkaLoss</code> with these parameters:

  {
      "loss": "CoSENTLoss",
      "matryoshka_dims": [
          768,
          512,
          256,
          128,
          64
      ],
      "matryoshka_weights": [
          1,
          1,
          1,
          1,
          1
      ],
      "n_dims_per_step": -1
  }

Training Hyperparameters

Non-Default Hyperparameters

• —eval_strategy: steps
• —per_device_train_batch_size: 16
• —per_device_eval_batch_size: 16
• —num_train_epochs: 5
• —warmup_ratio: 0.1
• —bf16: True

All Hyperparameters

<details><summary>Click to expand</summary>

• —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: 5e-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: 5
• —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: True
• —fp16: False
• —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: {'minnumparams': 0, 'xla': False, 'xlafsdpv2': False, 'xlafsdpgrad_ckpt': False}
• —fsdp_transformer_layer_cls_to_wrap: None
• —accelerator_config: {'splitbatches': False, 'dispatchbatches': None, 'evenbatches': True, 'useseedablesampler': True, 'nonblocking': False, 'gradientaccumulationkwargs': 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: None
• —hub_model_id: None
• —hub_strategy: every_save
• —hub_private_repo: None
• —hub_always_push: False
• —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
• —dispatch_batches: None
• —split_batches: 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
• —eval_use_gather_object: False
• —average_tokens_across_devices: False
• —prompts: None
• —batch_sampler: batch_sampler
• —multi_dataset_batch_sampler: proportional

</details>

Training Logs

Framework Versions

• —Python: 3.10.12
• —Sentence Transformers: 3.3.1
• —Transformers: 4.48.0
• —PyTorch: 2.5.1+cu121
• —Accelerate: 1.2.1
• —Datasets: 3.2.0
• —Tokenizers: 0.21.0

Citation

BibTeX

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",
}

MatryoshkaLoss

@misc{kusupati2024matryoshka,
    title={Matryoshka Representation Learning},
    author={Aditya Kusupati and Gantavya Bhatt and Aniket Rege and Matthew Wallingford and Aditya Sinha and Vivek Ramanujan and William Howard-Snyder and Kaifeng Chen and Sham Kakade and Prateek Jain and Ali Farhadi},
    year={2024},
    eprint={2205.13147},
    archivePrefix={arXiv},
    primaryClass={cs.LG}
}

CoSENTLoss

@online{kexuefm-8847,
    title={CoSENT: A more efficient sentence vector scheme than Sentence-BERT},
    author={Su Jianlin},
    year={2022},
    month={Jan},
    url={https://kexue.fm/archives/8847},
}

<!--

Glossary

Clearly define terms in order to be accessible across audiences. -->

<!--

Model Card Authors

Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction. -->

<!--

Model Card Contact

Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors. -->