Model reference · open weights

bert-hash-nano-embeddings-litert

Embeddings NeuML Embeddings 1 build Open weights 808 dl/mo

bert-hash-nano-embeddings-litert is an open-weight embedding model from NeuML.

  • bert-hash-nano-embeddings-litert is a sentence-similarity model developed by NeuML.
  • It is designed for embedding text to support search and similarity tasks, and it can be run using the txtai library.
  • The model is distributed under the apache-2.0 licence.

Summary of the NeuML/bert-hash-nano-embeddings-litert model card, 2026-10-01

What it is

Released byNeuML
Released2026-05-19

From the model card

What NeuML says about bert-hash-nano-embeddings-litert

Read the model card

bert-hash-nano-embeddings LiteRT model.

This can be run in txtai using the following code.

import txtai

embeddings = txtai.Embeddings(
  path="neuml/bert-hash-nano-embeddings-litert/bert-hash-nano-embeddings-fp16.tflite",
  content=True,
)
embeddings.index(documents())

# Run a query
embeddings.search("query to run")

See this link to see the code used to create this model.

Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.

How it works

How embedding models work

Your textsentence / documentEncodermaps meaningVectorlist of numbersAn embedding model turns text into a vector, so similar meanings sit close together, which is the basis of search and RAG.
© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms