No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from vllm-sr/Vela-1.0-Encoder-307M-FactCheck
All models by vllm-sr →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.
Compared with the original mmBERT32K FactCheck model for identifying requests that need fact-checking. Scores are on a 0–100 scale; higher is better.
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.
With PyTorch and Transformers 4.57.6 or 5.17.0:
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))