README.md

---
library_name: transformers
license: apache-2.0
pipeline_tag: text-classification
base_model: vllm-sr/Vela-1.0-Encoder-307M
base_model_relation: finetune
tags:
- semantic-router
- vela
- modernbert
---

<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 FactCheck

Vela FactCheck identifies requests that need external factual knowledge or retrieval; it does not determine whether a claim is true.

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

## Evaluation

Compared with [the original mmBERT32K FactCheck model](https://huggingface.co/vllm-sr/mmbert32k-factcheck-classifier-merged) for identifying requests that need fact-checking. Scores are on a 0–100 scale; higher is better.

| Development evaluation | Original mmBERT | Vela |
|---|---:|---:|
| Macro F1 · 186 inputs | 50.26 | **88.08** |
| Accuracy · 186 inputs | 54.30 | **88.17** |

The same 186 reviewed natural requests contain 7–2,868 tokens. Both models use FP32, complete inputs and the highest-scoring label. This development set informed Vela selection; it is not an independent test or a measurement of 32K accuracy.

## Quick start

With PyTorch and Transformers 4.57.6 or 5.17.0:

```python
from transformers import pipeline

model_id = "vllm-sr/Vela-1.0-Encoder-307M-FactCheck"
model = pipeline("text-classification", model=model_id, device=-1)
print(model("When was the first moon landing?", top_k=None, truncation=False))
```

[Explore the Vela model collection](https://huggingface.co/collections/vllm-sr/vela-10-router-models-6aa555ba70cc6997d6d67798)