BERT

Model name: bert_local

About BERT

BERT (Bidirectional Encoder Representations from Transformers) is a transformer-based model that's used for natural language processing tasks such as text classification, text generation, and text completion. It's pre-trained on a large corpus of text data and is capable of performing a wide range of natural language processing tasks.

Read more about BERT on Wikipedia and at Sentence Transformers on the Hugging Face website.

Supported aidb operations

encode_text
encode_text_batch

Supported models

sentence-transformers/all-MiniLM-L6-v2 (default)
sentence-transformers/all-MiniLM-L6-v1
sentence-transformers/all-MiniLM-L12-v1
sentence-transformers/msmarco-bert-base-dot-v5
sentence-transformers/multi-qa-MiniLM-L6-dot-v1
sentence-transformers/paraphrase-TinyBERT-L6-v2
sentence-transformers/all-distilroberta-v1
sentence-transformers/all-MiniLM-L6-v2
sentence-transformers/multi-qa-MiniLM-L6-cos-v1
sentence-transformers/paraphrase-multilingual-mpnet-base-v2
sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2

Creating the default model

SELECT aidb.create_model('my_bert_model', 'bert_local');

Creating a specific model

You can specify a model and revision in the options JSONB object. This example creates a sentence-transformers/all-distilroberta-v1 model with the name another_bert_model:

select aidb.create_model(
  'another_bert_model',
  'bert_local',
  '{"model": "sentence-transformers/all-distilroberta-v1", "revision": "main"}'::JSONB 
)

Model configuration settings

The following configuration settings are available for BERT models:

model — The BERT model to use. The default is sentence-transformers/all-MiniLM-L6-v2.
revision — The revision of the model to use. The default is refs/pr/64. This entry is a reference to the model revision in the Hugging Face repository. It's used to specify the model version to use, in this case this branch.