Modernbert Embed Base Legal MRL

🚀 ModernBERT Embed base Legal Matryoshka

这是一个基于 sentence-transformers 的模型，它在 AdamLucek/legal-rag-positives-synthetic 数据集上对 nomic-ai/modernbert-embed-base 进行了微调。该模型可以将句子和段落映射到一个 768 维的密集向量空间，可用于语义文本相似度计算、语义搜索、释义挖掘、文本分类、聚类等任务。

🚀 快速开始

直接使用（Sentence Transformers）

首先安装 Sentence Transformers 库：

pip install -U sentence-transformers

然后，你可以加载这个模型并进行推理：

from sentence_transformers import SentenceTransformer

# 从 🤗 Hub 下载
model = SentenceTransformer("AdamLucek/ModernBERT-embed-base-legal-MRL")
# 进行推理
sentences = [
    'contracting/contracting-assistance-programs/sba-mentor-protege-program (last visited Apr. 19, \n2023). \n5 \n \nprotégé must demonstrate that the added mentor-protégé relationship will not adversely affect the \ndevelopment of either protégé firm (e.g., the second firm may not be a competitor of the first \nfirm).”  13 C.F.R. § 125.9(b)(3).',
    'What must the protégé demonstrate about the mentor-protégé relationship?',
    'What discretion do district courts have regarding a defendant’s invocation of FOIA exemptions?',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# 获取嵌入向量的相似度得分
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

✨ 主要特性

该模型具有以下特性：

• 能够将句子和段落映射到 768 维的密集向量空间。
• 可用于语义文本相似度、语义搜索、释义挖掘、文本分类、聚类等多种任务。

📦 安装指南

安装 Sentence Transformers 库：

pip install -U sentence-transformers

📚 详细文档

模型详情

模型描述

完整模型架构

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()
)

评估

指标

信息检索

训练详情

AdamLucek/legal-rag-positives-synthetic

• 数据集：AdamLucek/legal-rag-positives-synthetic
• 大小：5822 个训练样本
• 列：positive 和 anchor
• 基于前 1000 个样本的近似统计信息： | | positive | anchor | | ---- | ---- | ---- | | 类型 | 字符串 | 字符串 | | 详情 |
  • 最小：15 个标记
  • 平均：97.6 个标记
  • 最大：153 个标记
  |
  • 最小：8 个标记
  • 平均：16.68 个标记
  • 最大：41 个标记
  |
• 样本： | positive | anchor | | ---- | ---- | | infrastructure security information,” the information at issue must, “if disclosed . . . reveal vulner-
abilities in Department of Defense critical infrastructure.” 10 U.S.C. § 130e(f). The closest the
Department comes is asserting that the information “individually or in the aggregate, would enable | What type of information must reveal vulnerabilities if disclosed? | | they have bid.” Oral Arg. Tr. at 42:18–20. Plaintiffs also assert that, should this Court require the
Polaris Solicitations to consider price at the IDIQ level, such an adjustment “adds a solicitation
requirement that would necessarily change the overall structure of the evaluation” GSA must
perform in awarding the IDIQ contracts. Oral Arg. Tr. at 43:3–5; see supra Discussion Section | Where in the document can further discussion about the assertion be found? | | otra parte. Fernández v. San Juan Cement Co., Inc., 118 DPR 713,
718-719 (1987). Nuestro más Alto Foro ha dispuesto que, la
facultad de imponer honorarios de abogados es la mejor arma que

22 Id.
23 Andamios de PR v. Newport Bonding, 179 DPR 503, 520 (2010); Pérez Rodríguez
v. López Rodríguez, supra; SLG González -Figueroa v. Pacheco Romero, supra; | What case is cited with the reference number 118 DPR 713? |
• 损失函数：MatryoshkaLoss，参数如下：

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

训练超参数

非默认超参数

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

所有超参数

训练日志

• 加粗行表示保存的检查点。

框架版本

• Python: 3.11.11
• 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

📄 许可证

本模型使用 apache-2.0 许可证。

📖 引用

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}
}