README.md

metadata

tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:8963241
  - loss:EmbedDistillLoss
base_model: answerdotai/ModernBERT-large
widget:
  - source_sentence: >-
      A man in shorts and a woman in a black and white polka dot bikini
      sunbathing on the beach.
    sentences:
      - A man is standing in a field with a green plant in it.
      - A woman preparing some pork.
      - uh-huh uh-huh well what other movies have you seen then lately
  - source_sentence: A man is standing in a forest practicing a martial art.
    sentences:
      - >-
        Two men are standing in a room, pointing in opposite directions, while
        another man is standing in between them looking to his left.
      - A woman in a white button up shirt is holding a rope and smiling.
      - >-
        And a special In Madrid, thanks to the siesta lunch break, the rush hour
        happens not twice, but three times a day.
  - source_sentence: A Boston Terrier is running on lush green grass in front of a white fence.
    sentences:
      - >-
        The distinctive, sculpted marble figures of the era are now being
        reproduced in vast quantities as souvenirs.
      - An older lady in a blue shirt in a rowboat.
      - >-
        A man wearing jeans and no shirt is midair doing a kick flip on a
        skateboard.
  - source_sentence: Two dogs are chasing a ball.
    sentences:
      - >-
        I loved you that first moment in the car when the bullet grazed your
        cheek… . Five minutes later Jane murmured softly: "I don't know London
        very well, Julius, but is it such a very long way from the Savoy to the
        Ritz?"
      - A person is sleeping on a bench, next to cars.
      - >-
        One of the more scenic is the five-mile River Mountain Trail, which
        offers fine views of both Lake Mead and the Las Vegas Valley.
  - source_sentence: A woman in purple riding a brown horse, competitively.
    sentences:
      - >-
        and uh they they have designated smoking but it's just wide open it's
        not ventilated properly and i think that's bad but as far as the drugs
        you know being in the factory kind of environment that way
      - 1.5, formerly methodology transfer paper 5. Using Statistical Sampling.
      - >-
        The oldest dances are survivors from Moorish times, and are usually
        performed in mountain villages.
pipeline_tag: sentence-similarity
library_name: sentence-transformers
metrics:
  - pearson_cosine
  - spearman_cosine
model-index:
  - name: SentenceTransformer based on answerdotai/ModernBERT-large
    results:
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: sts dev
          type: sts-dev
        metrics:
          - type: pearson_cosine
            value: 0.8704018510417749
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.8718236865761443
            name: Spearman Cosine

SentenceTransformer based on answerdotai/ModernBERT-large

This is a sentence-transformers model finetuned from answerdotai/ModernBERT-large. 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: answerdotai/ModernBERT-large
• Maximum Sequence Length: 512 tokens
• Output Dimensionality: 1024 dimensions
• Similarity Function: Cosine Similarity
• Supported Modality: Text

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': 'ModernBertModel'})
  (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 in purple riding a brown horse, competitively.',
    "and uh they they have designated smoking but it's just wide open it's not ventilated properly and i think that's bad but as far as the drugs you know being in the factory kind of environment that way",
    'The oldest dances are survivors from Moorish times, and are usually performed in mountain villages.',
]
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, -0.0255,  0.1637],
#         [-0.0255,  1.0000,  0.0579],
#         [ 0.1637,  0.0579,  1.0000]])