onnx-ner-student

DeBERTa-v3-xsmall BIO token classifier distilled from the production GLiNER2 teacher (fastino/gliner2-base-v1) for résumé entity extraction. Replaces the ~1 GB GLiNER2 runtime in curriculo-ai to fit the t3.medium memory budget.

16 entity types, each an independent BIO sequence (a token may be B for several types at once — e.g. CI/CD is both technical_skill and framework).

Files

• model.onnx — FP32
• model_quantized.onnx — INT8 dynamic (runtime default)
• labels.json — the 16 type names, index-aligned to the output head
• tokenizer files (fast/tokenizers-loadable, torch-free)

I/O

input_ids, attention_mask [B, T] → logits [B, T, 16, 3] (argmax over the last dim → per-type BIO tag 0=O,1=B,2=I; decode with ner_dataset.decode_spans).

Results (held-out test vs teacher, best ct0.4_lr1e-04_ep6)

micro-F1 0.9173, precision 0.9123, recall 0.9224.

type	F1
award	0.9787
certification	0.896
degree	0.8894
field_of_study	0.9467
framework	0.8747
industry	0.9474
interest	0.9956
job_title	0.9242
language	1.0
location	0.9408
organization	0.9773
person_name	0.97
soft_skill	0.8229
technical_skill	0.8592
technology	0.9464
tool	0.8613