Vela-1.0-Encoder-307M-PII

<div align="center"> <img src="https://vllm-sr.ai/img/vllm-sr-logo.social.png" alt="vLLM Semantic Router" width="560" /> <p> <a href="https://vllm-sr.ai/"><strong>Docs</strong></a> | <a href="https://vllm-sr.ai/blog/"><strong>Blog</strong></a> | <a href="https://vllm-dev.slack.com/archives/C09CTGF8KCN"><strong>Slack</strong></a> | <a href="https://github.com/vllm-project/semantic-router"><strong>GitHub</strong></a> </p> </div>

Vela PII

Vela PII finds sensitive entity spans for privacy-aware routing and redaction.

307M parameters · Input capacity: 32,768 tokens, including special tokens.

Outputs use 35 BIO labels across 17 entity types. The example returns spans with Unicode character offsets.

Evaluation

Exact-span micro F1 (×100) on the same synthetic development sets, compared with the original mmBERT32K PII model. Higher is better.

Synthetic examples cover six languages. Long inputs include sparse entities, densely packed repeated entities and negative examples; micro F1 weights each entity equally. Both models process complete inputs in FP32 with the same exact-span scorer. These development sets informed Vela selection; they are not an independent natural-document benchmark.

Quick start

With PyTorch and Transformers 4.57.6 or 5.17.0:

from transformers import pipeline

model_id = "vllm-sr/Vela-1.0-Encoder-307M-PII"
model = pipeline("token-classification", model=model_id, aggregation_strategy="simple", device=-1)
text = "Contact Mara Wells at [email protected]."
assert len(model.tokenizer.encode(text)) <= model.model.config.max_position_embeddings
print(model(text))

Explore the Vela model collection