SentenceTransformer based on Alibaba-NLP/gte-large-en-v1.5

Model Details

Model Description

• Model Type: Sentence Transformer
• Base model: Alibaba-NLP/gte-large-en-v1.5
• Maximum Sequence Length: 8192 tokens
• Output Dimensionality: 1024 tokens
• 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': 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})
)

Usage

Direct Usage (Sentence Transformers)

Evaluation

Metrics

Information Retrieval

• Evaluated with InformationRetrievalEvaluator

Training Details

Training Dataset

Unnamed Dataset

• Size: 586 training samples
• Columns: sentence_0 and sentence_1
• Approximate statistics based on the first 586 samples:

  	sentence_0	sentence_1
  type	string	string
  details	min: 20 tokens mean: 35.95 tokens max: 60 tokens	min: 8 tokens mean: 545.8 tokens max: 1018 tokens

• Samples:

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

• Loss: MultipleNegativesRankingLoss with these parameters:
  json

  1{ 2 "scale": 20.0, 3 "similarity_fct": "cos_sim" 4}

Training Hyperparameters

Non-Default Hyperparameters

• 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

All Hyperparameters

Training Logs

Framework Versions

• 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

Citation

BibTeX

Sentence Transformers

MultipleNegativesRankingLoss