Revision Assistant โ€” Citation Need

Quantized ONNX + tokenizer for browser / Transformers.js inference in Revision Assistant.

Files

  • onnx/model_quantized.onnx โ€” int8 quantized weights (preferred for browser)
  • tokenizer + config.json / ort_config.json / inference_config.json

Metrics / inference config

{
  "threshold": 0.55,
  "base_model": "allenai/scibert_scivocab_uncased",
  "max_len": 96,
  "test_precision": 0.9414289028067734,
  "test_recall": 0.8224744148343297,
  "test_f1": 0.8779406197609648,
  "test_roc_auc": 0.9571438004475947,
  "n_train": 48000
}
Downloads last month
51
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support