You can deploy this model and start earning money today!

josh-oo/
BMRetriever-410M-sentence-transformer

Name: BMRetriever-410M-sentence-transformer
Availability: InStock

sentence-transformers

BMRetriever/BMRetriever-410M

finetune

endpoints_compatible

Views

No views yet

SentenceTransformer based on BMRetriever/BMRetriever-410M

This is a sentence-transformers model finetuned from BMRetriever/BMRetriever-410M. 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: BMRetriever/BMRetriever-410M
Maximum Sequence Length: 2048 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': 'GPTNeoXModel'})
  (1): Pooling({'embedding_dimension': 1024, 'pooling_mode': 'lasttoken', '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.

python

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("josh-oo/BMRetriever-410M-sentence-transformer")
# Run inference
sentences = [
    'The weather is lovely today.',
    "It's so sunny outside!",
    'He drove to the stadium.',
]
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, 0.9805, 0.9542],
#         [0.9805, 1.0000, 0.9605],
#         [0.9542, 0.9605, 1.0000]])

Training Details

Framework Versions

Python: 3.12.13
Sentence Transformers: 5.5.1
Transformers: 5.0.0
PyTorch: 2.11.0+cpu
Accelerate: 1.13.0
Datasets: 4.0.0
Tokenizers: 0.22.2