Views
No views yet
shawnw3i/Qwen3-Reranker-0.6B-ONNX (already quantized; a clean int8 build needs a fresh fp32
export — a future optimization).input_ids/attention_mask/position_ids
(int64); output logits [batch, seq, vocab]; take the last token, softmax over the
yes(9693)/no(2152) logits; P(yes) is the relevance score.model.onnx, tokenizer.json, config.json.benchmarks/onnx_models/prepare_models.py (used as-is, not re-quantized).