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-Halu
All models by vllm-sr →Vela Halu finds answer spans unsupported by the supplied evidence, for grounded answers and response verification.
307M parameters · Supported input length: 8,192 tokens, including special tokens.
Labels are supported (0) and hallucinated (1). Spans use Unicode character offsets in the answer. Evidence support is distinct from real-world factual truth; an empty result does not guarantee correctness.
Answers requiring arithmetic or multi-step reasoning beyond explicit context may be incorrectly flagged.
Reported scores on the 10,698-example fixed evaluation set. Each cell is Vela Halu / LettuceDetect, on a 0-100 scale; higher is better. Bold Vela scores exceed the paired baseline.
LettuceDetect scores are from its published model card, rounded to three decimal places on the 0-1 scale before conversion.
Span metrics measure character overlap; example F1 measures whether an answer contains any hallucinated span. IoU is mean character-set intersection over union. Vela evaluation uses bfloat16, an 8,192-token limit, only_first pair truncation, and token scores strictly above 0.5. Full scores include all source groups and truncation statistics.
With PyTorch and Transformers 4.57.6:
Keep the complete evidence, request and answer within the supported input length. The example checks this limit before inference.
import torchfrom transformers import AutoConfig, AutoModelForTokenClassification, AutoTokenizer
model_id = "vllm-sr/Vela-1.0-Encoder-307M-Halu"tokenizer = AutoTokenizer.from_pretrained(model_id, use_fast=True)config = AutoConfig.from_pretrained(model_id)config.reference_compile = Falsemodel = AutoModelForTokenClassification.from_pretrained( model_id, config=config, attn_implementation="sdpa").eval()
context = "The museum opens at 10:00 on Tuesday."question = "When does the museum open on Tuesday?"answer = "The museum opens at 09:00 on Tuesday."prompt = f"User request: {question}\n\n{context}"inputs = tokenizer(prompt, answer, return_offsets_mapping=True, return_tensors="pt", truncation=False)assert inputs.input_ids.shape[1] <= 8192sequence_ids = inputs.sequence_ids(0)offsets = inputs.pop("offset_mapping")[0].tolist()with torch.inference_mode(): scores = model(**inputs).logits.float().softmax(-1)[0, :, 1].tolist()
spans, current = [], Nonefor sequence, (start, end), score in zip(sequence_ids, offsets, scores): if sequence != 1 or end <= start: continue if score > 0.5: if current is None: current = {"start": start, "end": end} else: current["end"] = max(current["end"], end) elif current is not None: spans.append(current) current = Noneif current is not None: spans.append(current)print([{**span, "text": answer[span["start"]:span["end"]]} for span in spans])