aaa961/modernbert-embed-base-legal-matryoshka-corrected_train_set_anchor_positive_2026_03_09

SentenceTransformer based on aaa961/modernbert-embed-base-legal-matryoshka-2_2026-03-06

This is a sentence-transformers model finetuned from aaa961/modernbert-embed-base-legal-matryoshka-2_2026-03-06 on the json 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: aaa961/modernbert-embed-base-legal-matryoshka-2_2026-03-06 <!-- at revision c9b5f0f151ad5b7c1067e91db0503ac4a73ee9e9 -->
• —Maximum Sequence Length: 8192 tokens
• —Output Dimensionality: 768 dimensions
• —Similarity Function: Cosine Similarity
• —Training Dataset:
• —json <!-- - Language: Unknown --> <!-- - License: Unknown -->

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, 'architecture': '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("aaa961/modernbert-embed-base-legal-matryoshka-corrected_train_set_anchor_positive_2026_03_09")
# Run inference
sentences = [
    "To whom did the CIA's government counsel refer the plaintiff's counsel?",
    'CIA’s in-house journal Studies in Intelligence, see supra Part I.B.4, plaintiff’s counsel contacted \ngovernment counsel for the CIA, who referred plaintiff’s counsel to the FBI.  See Pl.’s First Mot. \nto Compel at 1.  In January 2012, an FBI field agent met with plaintiff’s counsel, at which time \nplaintiff’s counsel signed a non-disclosure agreement as to any classified material contained in',
    'favorably to his profile as a baseball player, and the fourth and fifth entries refer to his \ndefamation suit. While the fourth entry is headlined “Northwestern baseball player sued for \nintentional infliction of,” the text for that entry states: “For over two years, Chad Readey has \nbeen the victim of a vicious, coordinated effort to assassinate his character based on',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.7737, 0.4363],
#         [0.7737, 1.0000, 0.4764],
#         [0.4363, 0.4764, 1.0000]])

<!--

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

Information Retrieval

• —Dataset: dim_768
• —Evaluated with <code>InformationRetrievalEvaluator</code> with these parameters:

  {
      "truncate_dim": 768
  }

Information Retrieval

• —Dataset: dim_512
• —Evaluated with <code>InformationRetrievalEvaluator</code> with these parameters:

  {
      "truncate_dim": 512
  }

Information Retrieval

• —Dataset: dim_256
• —Evaluated with <code>InformationRetrievalEvaluator</code> with these parameters:

  {
      "truncate_dim": 256
  }

Information Retrieval

• —Dataset: dim_128
• —Evaluated with <code>InformationRetrievalEvaluator</code> with these parameters:

  {
      "truncate_dim": 128
  }

Information Retrieval

• —Dataset: dim_64
• —Evaluated with <code>InformationRetrievalEvaluator</code> with these parameters:

  {
      "truncate_dim": 64
  }

<!--

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

json

• —Dataset: json
• —Size: 5,822 training samples
• —Columns: <code>anchor</code> and <code>positive</code>
• —Approximate statistics based on the first 1000 samples: | | anchor | positive | |:--------|:----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------| | type | string | string | | details | <ul><li>min: 7 tokens</li><li>mean: 16.67 tokens</li><li>max: 39 tokens</li></ul> | <ul><li>min: 29 tokens</li><li>mean: 97.89 tokens</li><li>max: 170 tokens</li></ul> |
• —Samples: | anchor | positive | |:-----------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | <code>What is the case citation for Colón v. Romero Barceló?</code> | <code>13 Colón v. Romero Barceló, 112 DPR 573 (1982). <br> <br> <br> <br>KLAN202300916 <br> <br> <br> <br> <br>11<br> <br>Posteriormente, en López Tristani v. Maldonado Carrero, <br>supra, la Alta Curia puntualizó que la doctrina civilista reconocía el <br>derecho a la propia imagen como un derecho de la personalidad, <br>protegido por principios constitutivos del ordenamiento jurídico.</code> | | <code>Who became a major investor/shareholder?</code> | <code>exchange for 397,219 shares of DR’s Series Seed-1 Preferred Stock, becoming a <br>major investor/shareholder.7 Senetas invested in DR because DR “had a leading <br>medical application for artificial intelligence and machine learning, and had <br>assembled a team of the most expert people around the world that were assisting in</code> | | <code>Where is information about fee category not included, according to the CIA's declarant?</code> | <code>sort its incoming FOIA requests based on fee categories.” First Lutz Decl. ¶ 11. The CIA’s <br>declarant also states that “this information [i.e., fee category] is not included in the electronic <br>system,” though the CIA’s declarant also avers that “[f]ee category is not a mandatory field,” and <br>thus “this information is often not included in a FOIA request record.” Id. The plaintiff focuses</code> |
• —Loss: <code>MatryoshkaLoss</code> with these parameters:

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

Training Hyperparameters

Non-Default Hyperparameters

• —per_device_train_batch_size: 32
• —num_train_epochs: 4
• —learning_rate: 2e-05
• —lr_scheduler_type: cosine
• —warmup_steps: 0.1
• —optim: adamwtorchfused
• —gradient_accumulation_steps: 16
• —bf16: True
• —tf32: True
• —eval_strategy: epoch
• —per_device_eval_batch_size: 16
• —load_best_model_at_end: True
• —warmup_ratio: 0.1
• —batch_sampler: no_duplicates

All Hyperparameters

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

• —per_device_train_batch_size: 32
• —num_train_epochs: 4
• —max_steps: -1
• —learning_rate: 2e-05
• —lr_scheduler_type: cosine
• —lr_scheduler_kwargs: None
• —warmup_steps: 0.1
• —optim: adamwtorchfused
• —optim_args: None
• —weight_decay: 0.0
• —adam_beta1: 0.9
• —adam_beta2: 0.999
• —adam_epsilon: 1e-08
• —optim_target_modules: None
• —gradient_accumulation_steps: 16
• —average_tokens_across_devices: True
• —max_grad_norm: 1.0
• —label_smoothing_factor: 0.0
• —bf16: True
• —fp16: False
• —bf16_full_eval: False
• —fp16_full_eval: False
• —tf32: True
• —gradient_checkpointing: False
• —gradient_checkpointing_kwargs: None
• —torch_compile: False
• —torch_compile_backend: None
• —torch_compile_mode: None
• —use_liger_kernel: False
• —liger_kernel_config: None
• —use_cache: False
• —neftune_noise_alpha: None
• —torch_empty_cache_steps: None
• —auto_find_batch_size: False
• —log_on_each_node: True
• —logging_nan_inf_filter: True
• —include_num_input_tokens_seen: no
• —log_level: passive
• —log_level_replica: warning
• —disable_tqdm: False
• —project: huggingface
• —trackio_space_id: trackio
• —eval_strategy: epoch
• —per_device_eval_batch_size: 16
• —prediction_loss_only: True
• —eval_on_start: False
• —eval_do_concat_batches: True
• —eval_use_gather_object: False
• —eval_accumulation_steps: None
• —include_for_metrics: []
• —batch_eval_metrics: False
• —save_only_model: False
• —save_on_each_node: False
• —enable_jit_checkpoint: False
• —push_to_hub: False
• —hub_private_repo: None
• —hub_model_id: None
• —hub_strategy: every_save
• —hub_always_push: False
• —hub_revision: None
• —load_best_model_at_end: True
• —ignore_data_skip: False
• —restore_callback_states_from_checkpoint: False
• —full_determinism: False
• —seed: 42
• —data_seed: None
• —use_cpu: False
• —accelerator_config: {'splitbatches': False, 'dispatchbatches': None, 'evenbatches': True, 'useseedablesampler': True, 'nonblocking': False, 'gradientaccumulationkwargs': None}
• —parallelism_config: None
• —dataloader_drop_last: False
• —dataloader_num_workers: 0
• —dataloader_pin_memory: True
• —dataloader_persistent_workers: False
• —dataloader_prefetch_factor: None
• —remove_unused_columns: True
• —label_names: None
• —train_sampling_strategy: random
• —length_column_name: length
• —ddp_find_unused_parameters: None
• —ddp_bucket_cap_mb: None
• —ddp_broadcast_buffers: False
• —ddp_backend: None
• —ddp_timeout: 1800
• —fsdp: []
• —fsdp_config: {'minnumparams': 0, 'xla': False, 'xlafsdpv2': False, 'xlafsdpgrad_ckpt': False}
• —deepspeed: None
• —debug: []
• —skip_memory_metrics: True
• —do_predict: False
• —resume_from_checkpoint: None
• —warmup_ratio: 0.1
• —local_rank: -1
• —prompts: None
• —batch_sampler: no_duplicates
• —multi_dataset_batch_sampler: proportional
• —router_mapping: {}
• —learning_rate_mapping: {}

</details>

Training Logs

• —The bold row denotes the saved checkpoint.

Framework Versions

• —Python: 3.12.11
• —Sentence Transformers: 5.2.3
• —Transformers: 5.3.0
• —PyTorch: 2.5.1+cu121
• —Accelerate: 1.13.0
• —Datasets: 4.6.1
• —Tokenizers: 0.22.2

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}
}

MultipleNegativesRankingLoss

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply},
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}

<!--

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. -->