metadata

pipeline_tag: sentence-similarity
tags:
  - sentence-transformers
  - feature-extraction
  - sentence-similarity

query2query

This is a sentence-transformers model: It maps queries to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search over queries.

Usage (Sentence-Transformers)

Using this model becomes easy when you have sentence-transformers installed:

pip install -U sentence-transformers

Then you can use the model like this:

from sentence_transformers import SentenceTransformer
queries = ["flight cost from nyc to la", "ticket prices from nyc to la"]

model = SentenceTransformer('{MODEL_NAME}')
embeddings = model.encode(queries)
print(embeddings)

Training

The model was trained for 1M steps with a batch size of 1024 at a learning rate of 2e-5 using a cosine learning rate scheduler with 10000 warmup steps.

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: DataParallel 
  (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})
  (2): Normalize()
)