parte_3 / README.md
andreyunic23's picture
Upload 12 files
5fc50ec verified
metadata
base_model: sentence-transformers/all-MiniLM-L6-v2
library_name: sentence-transformers
pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:723
  - loss:ContrastiveTensionLossInBatchNegatives
widget:
  - source_sentence: During a rejected takeoff the aircraft departs runway.
    sentences:
      - The ship is approaching shallow water.
      - During a rejected takeoff the aircraft departs runway.
      - A/C must maintain minimum safe altitude limits.
  - source_sentence: ACS must provide attitude maneuver commands when ASTRO-H is rotating.
    sentences:
      - >-
        Laboratories that handle energetic materials must have laboratory
        environmental control equipment.
      - >-
        Loss of functioning democratic society (e.g. loss of freedom, human
        right .etc.).
      - ACS must provide attitude maneuver commands when ASTRO-H is rotating.
  - source_sentence: Overpressurization of plant equipment.
    sentences:
      - Low fuel level after missed approaches.
      - Overpressurization of plant equipment.
      - >-
        Aircraft comes too close to service equipment components during
        operations on the ground.
  - source_sentence: >-
      All the safety/mission critical military aerospace designs and products
      shall be Certified to allow use or operation.
    sentences:
      - >-
        Brake light command must illuminate early within X-seconds before
        stopping vehicle.
      - >-
        All the safety/mission critical military aerospace designs and products
        shall be Certified to allow use or operation.
      - ASTRO-H unable to collect scientific data.
  - source_sentence: Laboratory equipment out of calibration standards.
    sentences:
      - >-
        Certification Authority personal, including Organization Designation
        Authorization (ODA), unqualified to the product in analyse or at the
        certification process.
      - Staff suffers injury (radiological or physical).
      - Laboratory equipment out of calibration standards.

SentenceTransformer based on sentence-transformers/all-MiniLM-L6-v2

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L6-v2. It maps sentences & paragraphs to a 384-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: sentence-transformers/all-MiniLM-L6-v2
  • Maximum Sequence Length: 256 tokens
  • Output Dimensionality: 384 tokens
  • Similarity Function: Cosine Similarity

Model Sources

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 384, '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("sentence_transformers_model_id")
# Run inference
sentences = [
    'Laboratory equipment out of calibration standards.',
    'Laboratory equipment out of calibration standards.',
    'Staff suffers injury (radiological or physical).',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

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

Training Details

Training Dataset

Unnamed Dataset

  • Size: 723 training samples
  • Columns: sentence1, sentence2, and label
  • Approximate statistics based on the first 723 samples:
    sentence1 sentence2 label
    type string string int
    details
    • min: 4 tokens
    • mean: 13.84 tokens
    • max: 45 tokens
    • min: 4 tokens
    • mean: 13.84 tokens
    • max: 45 tokens
    • 0: 100.00%
  • Samples:
    sentence1 sentence2 label
    Non-patient injured or killed due to radiation. Non-patient injured or killed due to radiation. 0
    Loss of human life / damage to health and wellbeing (e.g. long term concerns with COVID). Loss of human life / damage to health and wellbeing (e.g. long term concerns with COVID). 0
    The aircraft have insufficient power available. The aircraft have insufficient power available. 0
  • Loss: ContrastiveTensionLossInBatchNegatives

Framework Versions

  • Python: 3.10.12
  • Sentence Transformers: 3.2.1
  • Transformers: 4.45.2
  • PyTorch: 2.5.0+cu121
  • Accelerate: 1.0.1
  • Datasets: 3.0.2
  • Tokenizers: 0.20.1

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",
}

ContrastiveTensionLossInBatchNegatives

@inproceedings{carlsson2021semantic,
    title={Semantic Re-tuning with Contrastive Tension},
    author={Fredrik Carlsson and Amaru Cuba Gyllensten and Evangelia Gogoulou and Erik Ylip{"a}{"a} Hellqvist and Magnus Sahlgren},
    booktitle={International Conference on Learning Representations},
    year={2021},
    url={https://openreview.net/forum?id=Ov_sMNau-PF}
}