README.md

metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:80
  - loss:CoSENTLoss
base_model: abdeljalilELmajjodi/model
widget:
  - source_sentence: >-
      A woman wearing all white and eating, walks next to a man holding a
      briefcase.
    sentences:
      - A married couple is sleeping.
      - The people are eating omelettes.
      - Two adults walk across a street.
  - source_sentence: >-
      Woman in white in foreground and a man slightly behind walking with a sign
      for John's Pizza and Gyro in the background.
    sentences:
      - There are people waiting on a train.
      - The family is outside.
      - The man with the sign is caucasian.
  - source_sentence: Two blond women are hugging one another.
    sentences:
      - The women are sleeping.
      - Olympic swimming.
      - A couple are playing frisbee with a young child at the beach.
  - source_sentence: >-
      Woman in white in foreground and a man slightly behind walking with a sign
      for John's Pizza and Gyro in the background.
    sentences:
      - The woman is wearing black.
      - They are smiling at their parents
      - The woman and man are playing baseball together.
  - source_sentence: >-
      A woman is walking across the street eating a banana, while a man is
      following with his briefcase.
    sentences:
      - A school is hosting an event.
      - There are people just getting on a train
      - An actress and her favorite assistant talk a walk in the city.
pipeline_tag: sentence-similarity
library_name: sentence-transformers

SentenceTransformer based on abdeljalilELmajjodi/model

This is a sentence-transformers model finetuned from abdeljalilELmajjodi/model on the all-nli dataset. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for retrieval.

Model Details

Model Description

• Model Type: Sentence Transformer
• Base model: abdeljalilELmajjodi/model
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 1024 dimensions
• Similarity Function: Cosine Similarity
• Supported Modality: Text
• Training Dataset:
  • all-nli

Model Sources

• Documentation: Sentence Transformers Documentation
• Repository: Sentence Transformers on GitHub
• Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'transformer_task': 'feature-extraction', 'modality_config': {'text': {'method': 'forward', 'method_output_name': 'last_hidden_state'}}, 'module_output_name': 'token_embeddings', 'architecture': 'XLMRobertaModel'})
  (1): Pooling({'embedding_dimension': 1024, 'pooling_mode': 'mean', 'include_prompt': True})
)

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 = [
    'A woman is walking across the street eating a banana, while a man is following with his briefcase.',
    'An actress and her favorite assistant talk a walk in the city.',
    'A school is hosting an event.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 1024]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities)
# tensor([[1.0000, 0.9934, 0.9887],
#         [0.9934, 1.0000, 0.9916],
#         [0.9887, 0.9916, 1.0000]])

Training Details

Training Dataset

all-nli

• Dataset: all-nli
• Size: 80 training samples
• Columns: sentence1, sentence2, and score
• Approximate statistics based on the first 80 samples:

  	sentence1	sentence2	score
  type	string	string	float
  details	min: 10 tokens mean: 25.77 tokens max: 52 tokens	min: 6 tokens mean: 12.45 tokens max: 29 tokens	min: 0.0 mean: 0.51 max: 1.0

• Samples:

  sentence1	sentence2	score
  Two adults, one female in white, with shades and one male, gray clothes, walking across a street, away from a eatery with a blurred image of a dark colored red shirted person in the foreground.	Two adults walk across the street.	1.0
  Woman in white in foreground and a man slightly behind walking with a sign for John's Pizza and Gyro in the background.	The man is sitting down while he has a sign for John's Pizza and Gyro in his arms.	0.0
  High fashion ladies wait outside a tram beside a crowd of people in the city.	The women do not care what clothes they wear.	0.0

• Loss: CoSENTLoss with these parameters:

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

Evaluation Dataset

all-nli

• Dataset: all-nli
• Size: 20 evaluation samples
• Columns: sentence1, sentence2, and score
• Approximate statistics based on the first 20 samples:

  	sentence1	sentence2	score
  type	string	string	float
  details	min: 10 tokens mean: 25.55 tokens max: 52 tokens	min: 5 tokens mean: 10.1 tokens max: 17 tokens	min: 0.0 mean: 0.47 max: 1.0

• Samples:

  sentence1	sentence2	score
  A couple play in the tide with their young son.	The family is outside.	1.0
  Two blond women are hugging one another.	The women are sleeping.	0.0
  Children smiling and waving at camera	They are smiling at their parents	0.5

• Loss: CoSENTLoss with these parameters:

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

Framework Versions

• Python: 3.12.13
• Sentence Transformers: 5.4.1
• Transformers: 5.0.0
• PyTorch: 2.10.0+cu128
• Accelerate: 1.13.0
• Datasets: 4.8.5
• 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",
}

CoSENTLoss

@article{10531646,
    author={Huang, Xiang and Peng, Hao and Zou, Dongcheng and Liu, Zhiwei and Li, Jianxin and Liu, Kay and Wu, Jia and Su, Jianlin and Yu, Philip S.},
    journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
    title={CoSENT: Consistent Sentence Embedding via Similarity Ranking},
    year={2024},
    doi={10.1109/TASLP.2024.3402087}
}