bionerd-re — C (BiomedBERT, BioRED typed relations)
BioNERD's own typed relation-extraction model "C": microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext (MIT) fine-tuned on the BioRED Train split (public domain) as an entity-marker sequence classifier.
- Input: text with
[E1] … [/E1]and[E2] … [/E2]around the two arguments (the four marker tokens are in the tokenizer). - Labels:
0 = None, then BioRED's eight types in this order: Association, Positive_Correlation, Negative_Correlation, Bind, Cotreatment, Comparison, Drug_Interaction, Conversion. - Training: seed 13, lr 2e-5, batch 16, up to 5 epochs, max length 512, 2 negatives per positive; the best epoch on BioRED Dev typed F1 was kept.
No accuracy is claimed here. BioNERD shows its measured labels in the app's model catalog, each tied to this exact artefact.
| File | sha256 |
|---|---|
| config.json | 6ac24d941178b632550aa2cb2c81594b9c88463bea01c32c5712064afbb23732 |
| model.safetensors | 7a96681585571fa82910d3e547bd71ff83eb5285c0859a37ae272116bbcca598 |
| tokenizer_config.json | 8b1605c818426817b2b46a1dbf23e834c7fc893a1a04cbda394382d719cb553a |
| tokenizer.json | 8c801ddf1fd1e9591578b90b7e3fa2bc895d80af941ae967f1f1869ea75aaca4 |