Yesterday
-
Link the in-browser demo Space and describe the ONNX files
-
Add ONNX exports for in-browser use (Transformers.js): fp32 and per-channel int8
Checked on the 763-review held-out split: fp32 identical to PyTorch (F1 0.885); per-channel MatMul int8 F1 0.891 with 1 decision flip. -
Add confusion matrix, probability and F1 charts, and held-out examples to model card
2 days ago
-
Upload held_out_metrics.json with huggingface_hub
-
Upload README.md with huggingface_hub
-
Upload tokenizer
-
Upload BertForSequenceClassification
-
initial commit
