Model reference · open weights

kobert

Available as managed deployment Embeddings monologg · community Embeddings 1 variants 21k dl/mo

kobert is an open-weight embedding model from monologg. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

Released bymonologg
TypeEmbedding models
TaskEmbeddings
Parameters (lead)92M
Context512 tokens
Runs withtransformers
Released2022-03-02
Popularity21k downloads / month
LicenceOpen weights

About

What kobert is

How to use

If you want to import KoBERT tokenizer with AutoTokenizer, you should give trust_remote_code=True.

from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("monologg/kobert")
tokenizer = AutoTokenizer.from_pretrained("monologg/kobert", trust_remote_code=True)

Reference

  • https://github.com/SKTBrain/KoBERT

From the published model card. Full card on the HuggingFace links in the sidebar.

Using it via the API

Call it like any OpenAI endpoint

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

Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.

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