PubMedBERT is a BERT model pretrained on PubMed text, and it can be used to build embeddings through the sentence-transformers library, which is the main way to load and run embedding models like this 1. Hugging Face hosts sentence-transformers models and offers an SDK and training support for them 4, while Replicate can run hosted embedding models through its API 2.
- 1
Sentence Transformers (SBERT)sbert.netverified and signed
Python module for computing embeddings from text and training or fine-tuning embedding models, usable to load a PubMedBERT-based sentence embedding model 1.
official:SDK · sentence-transformers+24 community tools built for it
for agents: embedding · BERT · XLNet
- 2
Hugging Facehuggingface.coverified and signed
Hosts models and provides the huggingface-hub SDK and sentence-transformers training actions to fine-tune and run embedding models 4.
official:MCP server · @huggingface/mcp-clientSDK · huggingface-hubCLI · text-embeddings-inferencerepository · pwc-cliskill · hf-cli+23 community tools built for it
for agents: train-sentence-transformers · text_classification · nlp
- 3
Replicatereplicate.comverified and signed
Runs open-source embedding models through a cloud API, with a JavaScript client and hosted sentence embedding models 2.
+14 community tools built for it
for agents: creatorrr/all-mpnet-base-v2 · ibm-granite/granite-embedding-small-english-r2 · lucataco/qwen3-embedding-8b
Sources
- 1SentenceTransformers Documentation — Sentence Transformers documentationsbert.net · read 2026-10-29
- 2Replicate - Run AI with an APIreplicate.com · read 2026-10-29
- 4Hugging Face – The AI community building the future.huggingface.co · read 2026-10-29
For agents: the 10 actions behind this answer
embedding · sentence-transformers verified and signed
creatorrr/all-mpnet-base-v2 · creatorrr/all-mpnet-base-v2 verified and signed
Sentence embedding using mpnet
createEmbedding · OpenAI API verified and signed
Creates an embedding vector representing the input text.
train-sentence-transformers · train-sentence-transformers verified and signed
Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker, pair scoring for two-stage retrieval / pair classification
PDB · Microsoft.DiaSymReader verified and signed
graph_sage_predict · neo4j-gds found in code, not yet checked
Generates node embeddings using a previously trained GraphSAGE model from the model catalog (see graph_sage_train).
healthcare · NVIDIA NIM for GenMol verified and signed
Task: Healthcare
powerbi-modeling · powerbi-modeling verified and signed
Power BI semantic modeling assistant for building optimized data models. Use when working with Power BI semantic models, creating measures, designing star schemas, configuring relationships, implementing RLS, or optimizing model performance. Triggers on queries about DAX calculations, table relation
workers-ai-search-model · Cloudflare API verified and signed
Model Search
python · fastcore verified and signed
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.