Model reference · open weights
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 by | monologg |
|---|---|
| Type | Embedding models |
| Task | Embeddings |
| Parameters (lead) | 92M |
| Context | 512 tokens |
| Runs with | transformers |
| Released | 2022-03-02 |
| Popularity | 21k downloads / month |
| Licence | Open weights |
About
If you want to import KoBERT tokenizer with
AutoTokenizer, you should givetrust_remote_code=True.
from transformers import AutoModel, AutoTokenizer
model = AutoModel.from_pretrained("monologg/kobert")
tokenizer = AutoTokenizer.from_pretrained("monologg/kobert", trust_remote_code=True)
From the published model card. Full card on the HuggingFace links in the sidebar.
Using it via the API
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.