Model reference · open weights

SapBERT-from-PubMedBERT-fulltext

SapBERT-from-PubMedBERT-fulltext is an open-weight embedding model from cambridgeltl, 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 cambridgeltl 1 variants 1.4M downloads/mo
Request this model on EU hardware All served models Not on the shared API today — deployed on request.

About

What SapBERT-from-PubMedBERT-fulltext is

datasets: - UMLS [news] A cross-lingual extension of SapBERT will appear in the main onference of ACL 2021! <br [news] SapBERT will appear in the conference proceedings of NAACL 2021! SapBERT-PubMedBERT SapBERT by Liu et al. (2020). Trained with UMLS 2020AA (English only), using microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext as the base model. Expected input and output The input should be a string of biomedical entity names, e.g., "covid infection" or "Hydroxychloroquine". The [CLS] embedding of the last layer is regarded as the output. Extracting embeddings from SapBERT The following script converts a list of strings (entity names) into embeddings. For more details about training and eval, see SapBERT github repo. Citation

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

Makercambridgeltl
TypeEmbedding models
Parameters (lead)109M
Context512 tokens
Variants1
Runs withtransformers
Released2022-03-02
Popularity1.4M downloads / month
Likes78
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
SapBERT-from-PubMedBERT-fulltext109MBF16~0.3 GBWeights ↗

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys sapbert-from-pubmedbert-fulltext for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (sapbert-from-pubmedbert-fulltext 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":"sapbert-from-pubmedbert-fulltext","input":"text to embed"}'

Details

Languages, data & research

Languages

en

Tags

transformers pytorch tf jax safetensors bert feature-extraction biomedical lexical semantics bionlp biology science embedding entity linking

Papers

Licence

Open weights

Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗

Sources

Weights & code

Want SapBERT-from-PubMedBERT-fulltext 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