CoolFace
Modelpublic

llm-semantic-router/Vela-1.0-Encoder-307M-Domain

sourceHugging Faceapache-2.0updated 9d agoView on Hugging Face
1likes3.7kdownloads
Model Card

<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 Domain

Vela Domain identifies the subject of a request across 14 domains to help select relevant models and tools.

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

Evaluation

Macro F1 (×100) on the same development sets, compared with the original mmBERT32K Domain model. Higher is better.

EvaluationOriginal mmBERTVela
Short requests · 1,98866.3385.15
Controlled 4K context · 287.1471.19
Controlled 8K context · 281.7981.19
Controlled 16K context · 281.7981.19
Controlled 32K context · 281.7977.86

Short requests cover English, Chinese, Spanish, French, German and Japanese. Long-context evaluation uses 28 English/Chinese examples extended to each length. Both models process the complete input in FP32. These development sets informed Vela checkpoint selection; they are not an independent test set.

Quick start

With PyTorch and Transformers 4.57.6 or 5.17.0:

python
from transformers import pipeline

model_id = "llm-semantic-router/Vela-1.0-Encoder-307M-Domain"
model = pipeline("text-classification", model=model_id, device=-1)
print(model("Why do bond prices fall when interest rates rise?", top_k=None, truncation=False))

Explore the Vela model collection