Model reference · open weights

paraphrase-albert-small

paraphrase-albert-small is an open-weight embedding model from GPTCache, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.

Embeddings GPTCache 1 variants 306k downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

Specifications

What it is

MakerGPTCache
TypeEmbedding models
Context512 tokens
Variants1
Runs withtransformers
Released2023-05-09
Popularity306k downloads / month
Likes2
LicenceOpen weights

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 — the basis of search and RAG.

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

VariantParamsPrecisionVRAMFits 16 GBWeights
paraphrase-albert-small-v2BF16Weights ↗

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys gptcache-paraphrase-albert-small for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (gptcache-paraphrase-albert-small below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/embeddings \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gptcache-paraphrase-albert-small","input":"text to embed"}'

Details

Languages, data & research

Tags

transformers albert feature-extraction endpoints_compatible

Licence

Open weights

Open weights under mit — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want paraphrase-albert-small on EU-owned hardware?

Request this model on EU hardware See what’s served now

Explore

More embedding models

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms