Add distilled NER student ONNX (fp32 + int8)

README.md

@@ -0,0 +1,52 @@
+---
+license: mit
+library_name: onnx
+tags:
+- token-classification
+- ner
+- resume
+- distillation
+base_model: microsoft/deberta-v3-xsmall
+---
+
+# 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 |

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

labels.json

@@ -0,0 +1 @@
+["award", "certification", "degree", "field_of_study", "framework", "industry", "interest", "job_title", "language", "location", "organization", "person_name", "soft_skill", "technical_skill", "technology", "tool"]

metrics.json

@@ -0,0 +1,64 @@
+{
+  "config": {
+    "backbone": "microsoft/deberta-v3-xsmall",
+    "max_len": 96,
+    "batch_size": 32,
+    "weight_decay": 0.01,
+    "warmup": 0.1,
+    "dropout": 0.1,
+    "seed": 42,
+    "conf_threshold": 0.4,
+    "lr": 0.0001,
+    "epochs": 6,
+    "tag": "ct0.4_lr1e-04_ep6",
+    "out_dir": "/home/dev/nada/curriculo-models/ner_student/runs/ct0.4_lr1e-04_ep6"
+  },
+  "val": {
+    "micro_f1": 0.9116,
+    "precision": 0.9081,
+    "recall": 0.9151,
+    "support": 4667,
+    "per_type": {
+      "award": 0.9778,
+      "certification": 0.8,
+      "degree": 0.8116,
+      "field_of_study": 0.9364,
+      "framework": 0.8443,
+      "industry": 0.9531,
+      "interest": 0.9958,
+      "job_title": 0.9325,
+      "language": 0.9958,
+      "location": 0.927,
+      "organization": 0.9816,
+      "person_name": 0.9605,
+      "soft_skill": 0.7879,
+      "technical_skill": 0.8638,
+      "technology": 0.9506,
+      "tool": 0.8536
+    }
+  },
+  "test": {
+    "micro_f1": 0.9173,
+    "precision": 0.9123,
+    "recall": 0.9224,
+    "support": 4666,
+    "per_type": {
+      "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
+    }
+  }
+}

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1ef89a35116ed040a598a054553fdc5d4087d31136dbb1f097b7f5232369cd1
+size 282935436

model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb4ed965f3f1fb1b6e07940ffb2d003861fbd409e2ac8f8c2791ca5071186c6a
+size 82256421

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}