基于 Alibaba-NLP/gte-large-en-v1.5 的 SentenceTransformer

这是一个基于 Alibaba-NLP/gte-large-en-v1.5 微调的 sentence-transformers 模型。它将句子和段落映射到 1024 维的稠密向量空间，可用于语义文本相似度、语义搜索、复述挖掘、文本分类、聚类等任务。

模型详情

模型描述

• 模型类型： Sentence Transformer
• 基础模型： Alibaba-NLP/gte-large-en-v1.5 <!-- at revision 104333d6af6f97649377c2afbde10a7704870c7b -->
• 最大序列长度： 8192 tokens
• 输出维度： 1024 维
• 相似度函数： 余弦相似度 <!-- - 训练数据集： 未知 --> <!-- - 语言： 未知 --> <!-- - 许可证： 未知 -->

模型来源

• 文档： Sentence Transformers 文档
• 代码库： Sentence Transformers GitHub
• Hugging Face： Hugging Face 上的 Sentence Transformers

完整模型架构

SentenceTransformer(
  (0): Transformer({'max_seq_length': 8192, 'do_lower_case': False}) with Transformer model: NewModel 
  (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)

使用方法

直接使用（Sentence Transformers）

首先安装 Sentence Transformers 库：

pip install -U sentence-transformers

然后你可以加载此模型并运行推理。

from sentence_transformers import SentenceTransformer

# 从 🤗 Hub 下载
model = SentenceTransformer("sentence_transformers_model_id")
# 运行推理
sentences = [
    'What are some of the legal frameworks mentioned in the context that aim to protect personal information, and how do they relate to data privacy concerns?',
    "65. See, e.g., Scott Ikeda. Major Data Broker Exposes 235 Million Social Media Profiles in Data Lead: Info\nAppears to Have Been Scraped Without Permission. CPO Magazine. Aug. 28, 2020. https://\nwww.cpomagazine.com/cyber-security/major-data-broker-exposes-235-million-social-media-profiles-\nin-data-leak/; Lily Hay Newman. 1.2 Billion Records Found Exposed Online in a Single Server . WIRED,\nNov. 22, 2019. https://www.wired.com/story/billion-records-exposed-online/\n66.Lola Fadulu. Facial Recognition Technology in Public Housing Prompts Backlash . New York Times.\nSept. 24, 2019.\nhttps://www.nytimes.com/2019/09/24/us/politics/facial-recognition-technology-housing.html\n67. Jo Constantz. 'They Were Spying On Us': Amazon, Walmart, Use Surveillance Technology to Bust\nUnions. Newsweek. Dec. 13, 2021.\nhttps://www.newsweek.com/they-were-spying-us-amazon-walmart-use-surveillance-technology-bust-\nunions-1658603\n68. See, e.g., enforcement actions by the FTC against the photo storage app Everalbaum\n(https://www.ftc.gov/legal-library/browse/cases-proceedings/192-3172-everalbum-inc-matter), and\nagainst Weight Watchers and their subsidiary Kurbo(https://www.ftc.gov/legal-library/browse/cases-proceedings/1923228-weight-watchersww)\n69. See, e.g., HIPAA, Pub. L 104-191 (1996); Fair Debt Collection Practices Act (FDCPA), Pub. L. 95-109\n(1977); Family Educational Rights and Privacy Act (FERPA) (20 U.S.C. § 1232g), Children's Online\nPrivacy Protection Act of 1998, 15 U.S.C. 6501–6505, and Confidential Information Protection andStatistical Efficiency Act (CIPSEA) (116 Stat. 2899)\n70. Marshall Allen. You Snooze, You Lose: Insurers Make The Old Adage Literally True . ProPublica. Nov.\n21, 2018.\nhttps://www.propublica.org/article/you-snooze-you-lose-insurers-make-the-old-adage-literally-true\n71.Charles Duhigg. How Companies Learn Your Secrets. The New York Times. Feb. 16, 2012.\nhttps://www.nytimes.com/2012/02/19/magazine/shopping-habits.html72. Jack Gillum and Jeff Kao. Aggression Detectors: The Unproven, Invasive Surveillance Technology\nSchools are Using to Monitor Students. ProPublica. Jun. 25, 2019.\nhttps://features.propublica.org/aggression-detector/the-unproven-invasive-surveillance-technology-\nschools-are-using-to-monitor-students/\n73.Drew Harwell. Cheating-detection companies made millions during the pandemic. Now students are\nfighting back. Washington Post. Nov. 12, 2020.\nhttps://www.washingtonpost.com/technology/2020/11/12/test-monitoring-student-revolt/\n74. See, e.g., Heather Morrison. Virtual Testing Puts Disabled Students at a Disadvantage. Government\nTechnology. May 24, 2022.\nhttps://www.govtech.com/education/k-12/virtual-testing-puts-disabled-students-at-a-disadvantage;\nLydia X. Z. Brown, Ridhi Shetty, Matt Scherer, and Andrew Crawford. Ableism And Disability\nDiscrimination In New Surveillance Technologies: How new surveillance technologies in education,\npolicing, health care, and the workplace disproportionately harm disabled people . Center for Democracy\nand Technology Report. May 24, 2022.https://cdt.org/insights/ableism-and-disability-discrimination-in-new-surveillance-technologies-how-new-surveillance-technologies-in-education-policing-health-care-and-the-workplace-disproportionately-harm-disabled-people/\n69",
    '25 MP-2.3-002 Review and document accuracy, representativeness, relevance, suitability of data \nused at different stages of AI life cycle.  Harmful Bias and Homogenization ; \nIntellectual Property  \nMP-2.3-003 Deploy and document fact -checking techniques to verify the accuracy and \nveracity of information generated by GAI systems, especially when the \ninformation comes from multiple (or unknown) sources.  Information Integrity  \nMP-2.3-004 Develop and implement testing techniques to identify GAI produced content (e.g., synthetic media) that might be indistinguishable from human -generated content.  Information Integrity  \nMP-2.3-005 Implement plans for GAI systems to undergo regular adversarial testing to identify \nvulnerabilities and potential manipulation or misuse.  Information Security  \nAI Actor Tasks:  AI Development, Domain Experts, TEVV  \n \nMAP 3.4:  Processes for operator and practitioner proficiency with AI system performance and trustworthiness – and relevant \ntechnical standards and certifications – are defined, assessed, and documented.  \nAction ID  Suggested Action  GAI Risks  \nMP-3.4-001 Evaluate whether GAI operators and end -users can accurately understand \ncontent lineage and origin.  Human -AI Configuration ; \nInformation Integrity  \nMP-3.4-002 Adapt existing training programs to include modules on digital content \ntransparency.  Information Integrity  \nMP-3.4-003 Develop certification programs that test proficiency in managing GAI risks and \ninterpreting content provenance, relevant to specific industry and context.  Information Integrity  \nMP-3.4-004 Delineate human proficiency tests from tests of GAI capabilities.  Human -AI Configuration  \nMP-3.4-005 Implement systems to continually monitor and track the outcomes of human- GAI \nconfigurations for future refinement and improvements . Human -AI Configuration ; \nInformation Integrity  \nMP-3.4-006 Involve the end -users, practitioners, and operators in GAI system in prototyping \nand testing activities. Make sure these tests cover various scenarios , such as crisis \nsituations or ethically sensitive contexts.  Human -AI Configuration ; \nInformation Integrity ; Harmful Bias \nand Homogenization ; Dangerous , \nViolent, or Hateful Content  \nAI Actor Tasks: AI Design, AI Development, Domain Experts, End -Users, Human Factors, Operation and Monitoring',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# 获取嵌入的相似度分数
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

<!--

直接使用（Transformers）

<details><summary>点击查看 Transformers 中的直接用法</summary>

</details> -->

<!--

下游使用（Sentence Transformers）

你可以在自己的数据集上微调此模型。

<details><summary>点击展开</summary>

</details> -->

<!--

超出范围的使用

列出模型可能被预见的滥用方式，并说明用户不应该用该模型做什么。 -->

评估

指标

信息检索

• 使用 <code>InformationRetrievalEvaluator</code> 进行评估

<!--

偏见、风险和局限性

该模型有哪些已知或可预见的问题？你也可以在这里标记已知的失败案例或模型的弱点。 -->

<!--

建议

针对可预见的问题有哪些建议？例如，过滤显式内容。 -->

训练详情

训练数据集

未命名数据集

• 大小：586 个训练样本
• 列：<code>sentence_0</code> 和 <code>sentence_1</code>
• 基于前 586 个样本的近似统计信息：

  	sentence_0	sentence_1
  类型	字符串	字符串
  详情	<ul><li>最小值：20 tokens</li><li>平均值：35.95 tokens</li><li>最大值：60 tokens</li></ul>	<ul><li>最小值：8 tokens</li><li>平均值：545.8 tokens</li><li>最大值：1018 tokens</li></ul>

• 样本：

  sentence_0	sentence_1
  <code>What are the primary objectives outlined in the "Blueprint for an AI Bill of Rights" as it pertains to the American people?</code>	<code>BLUEPRINT FOR AN <br>AI B ILL OF <br>RIGHTS <br>MAKING AUTOMATED <br>SYSTEMS WORK FOR <br>THE AMERICAN PEOPLE <br>OCTOBER 2022</code>
  <code>In what ways does the document propose to ensure that automated systems are designed and implemented to benefit society?</code>	<code>BLUEPRINT FOR AN <br>AI B ILL OF <br>RIGHTS <br>MAKING AUTOMATED <br>SYSTEMS WORK FOR <br>THE AMERICAN PEOPLE <br>OCTOBER 2022</code>
  <code>What is the primary purpose of the Blueprint for an AI Bill of Rights as published by the White House Office of Science and Technology Policy in October 2022?</code>	<code>About this Document <br>The Blueprint for an AI Bill of Rights: Making Automated Systems Work for the American People was <br>published by the White House Office of Science and Technology Policy in October 2022. This framework was <br>released one year after OSTP announced the launch of a process to develop "a bill of rights for an AI-powered <br>world." Its release follows a year of public engagement to inform this initiative. The framework is available <br>online at: https://www.whitehouse.gov/ostp/ai-bill-of-rights <br>About the Office of Science and Technology Policy <br>The Office of Science and Technology Policy (OSTP) was established by the National Science and Technology <br>Policy, Organization, and Priorities Act of 1976 to provide the President and others within the Executive Office <br>of the President with advice on the scientific, engineering, and technological aspects of the economy, national <br>security, health, foreign relations, the environment, and the technological recovery and use of resources, among <br>other topics. OSTP leads interagency science and technology policy coordination efforts, assists the Office of <br>Management and Budget (OMB) with an annual review and analysis of Federal research and development in <br>budgets, and serves as a source of scientific and technological analysis and judgment for the President with <br>respect to major policies, plans, and programs of the Federal Government. <br>Legal Disclaimer <br>The Blueprint for an AI Bill of Rights: Making Automated Systems Work for the American People is a white paper <br>published by the White House Office of Science and Technology Policy. It is intended to support the <br>development of policies and practices that protect civil rights and promote democratic values in the building, <br>deployment, and governance of automated systems. <br>The Blueprint for an AI Bill of Rights is non-binding and does not constitute U.S. government policy. It <br>does not supersede, modify, or direct an interpretation of any existing statute, regulation, policy, or <br>international instrument. It does not constitute binding guidance for the public or Federal agencies and <br>therefore does not require compliance with the principles described herein. It also is not determinative of what <br>the U.S. government's position will be in any international negotiation. Adoption of these principles may not <br>meet the requirements of existing statutes, regulations, policies, or international instruments, or the <br>requirements of the Federal agencies that enforce them. These principles are not intended to, and do not, <br>prohibit or limit any lawful activity of a government agency, including law enforcement, national security, or <br>intelligence activities. <br>The appropriate application of the principles set forth in this white paper depends significantly on the <br>context in which automated systems are being utilized. In some circumstances, application of these principles <br>in whole or in part may not be appropriate given the intended use of automated systems to achieve government <br>agency missions. Future sector-specific guidance will likely be necessary and important for guiding the use of <br>automated systems in certain settings such as AI systems used as part of school building security or automated <br>health diagnostic systems. <br>The Blueprint for an AI Bill of Rights recognizes that law enforcement activities require a balancing of <br>equities, for example, between the protection of sensitive law enforcement information and the principle of <br>notice; as such, notice may not be appropriate, or may need to be adjusted to protect sources, methods, and <br>other law enforcement equities. Even in contexts where these principles may not apply in whole or in part, <br>federal departments and agencies remain subject to judicial, privacy, and civil liberties oversight as well as <br>existing policies and safeguards that govern automated systems, including, for example, Executive Order 13960, <br>Promoting the Use of Trustworthy Artificial Intelligence in the Federal Government (December 2020). <br>This white paper recognizes that national security (which includes certain law enforcement and <br>homeland security activities) and defense activities are of increased sensitivity and interest to our nation's <br>adversaries and are often subject to special requirements, such as those governing classified information and <br>other protected data. Such activities require alternative, compatible safeguards through existing policies that <br>govern automated systems and AI, such as the Department of Defense (DOD) AI Ethical Principles and <br>Responsible AI Implementation Pathway and the Intelligence Community (IC) AI Ethics Principles and <br>Framework. The implementation of these policies to national security and defense activities can be informed by <br>the Blueprint for an AI Bill of Rights where feasible.</code>

• 损失函数：带有以下参数的 <code>MultipleNegativesRankingLoss</code>：

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim"
  }
  

训练超参数

非默认超参数

• eval_strategy: steps
• per_device_train_batch_size: 5
• per_device_eval_batch_size: 5
• num_train_epochs: 2
• multi_dataset_batch_sampler: round_robin

所有超参数

<details><summary>点击展开</summary>

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 5
• per_device_eval_batch_size: 5
• 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
• num_train_epochs: 2
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.0
• 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: 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: {'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: None
• hub_model_id: None
• hub_strategy: every_save
• hub_private_repo: False
• hub_always_push: False
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• 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
• eval_use_gather_object: False
• batch_sampler: batch_sampler
• multi_dataset_batch_sampler: round_robin

</details>

训练日志

框架版本

• Python: 3.10.12
• Sentence Transformers: 3.1.1
• Transformers: 4.44.2
• PyTorch: 2.4.1+cu121
• Accelerate: 0.34.2
• Datasets: 3.0.1
• Tokenizers: 0.19.1

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",
}

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}
}

<!--

术语表

清晰地定义术语，以便不同受众都能理解。 -->

<!--

模型卡作者

列出创建模型卡的人员，为模型卡构建中的详细工作提供认可和责任归属。 -->

<!--

模型卡联系方式

为想要更新模型卡、提出建议或有疑问的人提供联系模型卡作者的方式。 -->