Model reference · open weights

unsup-simcse-xlm-roberta

Available as managed deployment Embeddings ZurichNLP Embeddings 1 variants 819 dl/mo

unsup-simcse-xlm-roberta is an open-weight embedding model from ZurichNLP. 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 byZurichNLP
TypeEmbedding models
TaskEmbeddings
Parameters (lead)277M
Context514 tokens
Runs withtransformers
Released2023-05-21
Popularity819 downloads / month
LicenceOpen weights

About

What unsup-simcse-xlm-roberta is

xlm-roberta-base fine-tuned for sentence embeddings with SimCSE (Gao et al., EMNLP 2021).

See a similar English model released by Gao et al.: https://huggingface.co/princeton-nlp/unsup-simcse-roberta-base.

Fine-tuning was done using the reference implementation of unsupervised SimCSE and the 1M sentences from English Wikipedia released by the authors. As a sentence representation, we used the average of the last hidden states (pooler_type=avg), which is compatible with Sentence-BERT.

Fine-tuning command:

python train.py \
    --model_name_or_path xlm-roberta-base \
    --train_file data/wiki1m_for_simcse.txt \
    --output_dir unsup-simcse-xlm-roberta-base \
    --num_train_epochs 1 \
    --per_device_train_batch_size 32 \
    --gradient_accumulation_steps 16 \
    --learning_rate 1e-5 \
    --max_seq_length 128 \
    --pooler_type avg \
    --overwrite_output_dir \
    --temp 0.05 \
    --do_train \
    --fp16 \
    --seed 28852
Read the full model card

Citation

@inproceedings{vamvas-sennrich-2023-rsd,
      title={Towards Unsupervised Recognition of Token-level Semantic Differences in Related Documents},
      author={Jannis Vamvas and Rico Sennrich},
      month = dec,
      year = "2023",
      booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
      address = "Singapore",
      publisher = "Association for Computational Linguistics",
}

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 unsup-simcse-xlm-roberta for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (unsup-simcse-xlm-roberta 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":"unsup-simcse-xlm-roberta","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