Model reference · open weights
star is an open-weight embedding model from AIDA-UPM. 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 | AIDA-UPM |
|---|---|
| Type | Embedding models |
| Task | Embeddings |
| Context | 514 tokens |
| Runs with | transformers |
| Released | 2023-10-05 |
| Popularity | 1k downloads / month |
| Licence | Unknown |
About
This is the repository for the Style Transformer for Authorship Representations (STAR) model. We present the weights of our model here.
Also check out our github repo for STAR for replication.
tokenizer = AutoTokenizer.from_pretrained('roberta-large')
model = AutoModel.from_pretrained('AIDA-UPM/star')
examples = ['My text 1', 'This is another text']
def extract_embeddings(texts):
encoded_texts = tokenizer(texts)
with torch.no_grad():
style_embeddings = model(encoded_texts.input_ids,
attention_mask=encoded_texts.attention_mask).pooler_output
return style_embeddings
print(extract_embeddings(examples))
@article{Huertas-Tato2023Oct,
author = {Huertas-Tato, Javier and Martin, Alejandro and Camacho, David},
title = {{Understanding writing style in social media with a supervised contrastively pre-trained transformer}},
journal = {arXiv},
year = {2023},
month = oct,
eprint = {2310.11081},
doi = {10.48550/arXiv.2310.11081}
}
From the published model card. Full card on the HuggingFace links in the sidebar.
Using it via the API
Once AxForge deploys star for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (star 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":"star","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.