Upload fine-tuned Thai Job NER model (v3, F1=0.897)

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,142 @@
+---
+language:
+  - th
+license: mit
+library_name: transformers
+tags:
+  - token-classification
+  - ner
+  - thai
+  - phayathaibert
+  - job-posting
+  - apple-silicon
+datasets:
+  - chayuto/thai-job-ner-dataset
+metrics:
+  - f1
+  - precision
+  - recall
+pipeline_tag: token-classification
+model-index:
+  - name: thai-job-ner-phayathaibert
+    results:
+      - task:
+          type: token-classification
+          name: Named Entity Recognition
+        metrics:
+          - name: F1
+            type: f1
+            value: 0.956
+          - name: Precision
+            type: precision
+            value: 0.939
+          - name: Recall
+            type: recall
+            value: 0.974
+---
+
+# Thai Job NER — Fine-tuned PhayaThaiBERT
+
+Named Entity Recognition model for extracting structured HR data from informal Thai job postings (e.g., Facebook groups, Line chats). Fine-tuned from [PhayaThaiBERT](https://huggingface.co/clicknext/phayathaibert) (~122M params).
+
+## Model Description
+
+This model extracts 7 entity types from Thai job-related text:
+
+| Entity | Description | Example |
+|--------|-------------|---------|
+| `HARD_SKILL` | Skills or procedures | ดูแลผู้สูงอายุ, CPR, Python |
+| `PERSON` | Names | คุณสมชาย, พี่แจน |
+| `LOCATION` | Places | สีลม, ลาดพร้าว, บางนา |
+| `COMPENSATION` | Pay amounts | 18,000 บาท/เดือน |
+| `EMPLOYMENT_TERMS` | Job structure | part-time, กะกลางวัน |
+| `CONTACT` | Phone, Line, email | 081-234-5678, @care123 |
+| `DEMOGRAPHIC` | Age, gender | อายุ 25-40, หญิง |
+
+## Usage
+
+```python
+from transformers import AutoTokenizer, AutoModelForTokenClassification, pipeline
+
+model_name = "chayuto/thai-job-ner-phayathaibert"
+ner = pipeline("ner", model=model_name, aggregation_strategy="simple")
+
+text = "รับสมัครคนดูแลผู้สูงอายุ ย่านสีลม เงินเดือน 18,000 บาท โทร 081-234-5678"
+results = ner(text)
+for entity in results:
+    print(f"{entity['entity_group']}: {entity['word']} ({entity['score']:.2%})")
+```
+
+## Training
+
+- **Base model:** `clicknext/phayathaibert` (CamemBERT architecture, ~122M params, XLM-R-derived vocabulary)
+- **Training data:** 1,253 Thai job posts (synthetic silver labels from GPT-4o, fuzzy-aligned to IOB2) — [Dataset on HuggingFace](https://huggingface.co/datasets/chayuto/thai-job-ner-dataset)
+- **Hardware:** Apple Silicon MPS backend, FP32
+- **Hyperparameters:** LR=3e-5, warmup=0.1, batch=2, grad_accum=8, 15 epochs, gradient checkpointing, frozen embeddings
+- **Training time:** ~10 min
+
+### Data Pipeline
+
+Raw Thai text + GPT-4o entity extractions → fuzzy alignment with rapidfuzz + pythainlp TCC boundary snapping → subword token mapping via offset_mapping → IOB2-formatted HuggingFace Dataset.
+
+## Evaluation
+
+### Overall (Test Set, 126 examples)
+
+| Metric | Score |
+|--------|-------|
+| **F1** | **0.956** |
+| Precision | 0.939 |
+| Recall | 0.974 |
+
+### Per-Entity F1
+
+| Entity | F1 | Precision | Recall |
+|--------|-----|-----------|--------|
+| CONTACT | 0.987 | 0.983 | 0.991 |
+| PERSON | 0.979 | 0.972 | 0.986 |
+| LOCATION | 0.966 | 0.950 | 0.983 |
+| EMPLOYMENT_TERMS | 0.966 | 0.943 | 0.990 |
+| COMPENSATION | 0.965 | 0.956 | 0.973 |
+| HARD_SKILL | 0.946 | 0.919 | 0.974 |
+| DEMOGRAPHIC | 0.915 | 0.897 | 0.935 |
+
+### Comparison vs WangchanBERTa
+
+| Entity | WangchanBERTa | PhayaThaiBERT | Delta |
+|--------|---------------|---------------|-------|
+| **Overall F1** | 0.897 | **0.956** | **+0.059** |
+| COMPENSATION | 0.764 | **0.965** | **+0.200** |
+| PERSON | 0.907 | **0.979** | **+0.072** |
+| HARD_SKILL | 0.903 | **0.946** | **+0.043** |
+| EMPLOYMENT_TERMS | 0.926 | **0.966** | +0.040 |
+| DEMOGRAPHIC | 0.875 | **0.915** | +0.041 |
+| CONTACT | 0.962 | **0.987** | +0.025 |
+| LOCATION | 0.959 | **0.966** | +0.008 |
+
+PhayaThaiBERT improves on every entity type, with the most dramatic gain on COMPENSATION (+0.200 F1).
+
+## Links
+
+- **Model:** [chayuto/thai-job-ner-phayathaibert](https://huggingface.co/chayuto/thai-job-ner-phayathaibert)
+- **WangchanBERTa variant:** [chayuto/thai-job-ner-wangchanberta](https://huggingface.co/chayuto/thai-job-ner-wangchanberta)
+- **Dataset:** [chayuto/thai-job-ner-dataset](https://huggingface.co/datasets/chayuto/thai-job-ner-dataset)
+- **Source Code:** [github.com/chayuto/thai-job-nlp-ner](https://github.com/chayuto/thai-job-nlp-ner)
+
+## Limitations
+
+- Trained on synthetic data — may underperform on real-world posts with heavy emoji usage, OCR errors, or extreme colloquialism
+- Embeddings were frozen during training (MPS memory constraint) — unfreezing on a larger GPU may yield further gains
+- 512 token max sequence length
+- Larger model file size due to 248K vocabulary (vs WangchanBERTa's 25K)
+
+## Technical Notes
+
+- **FP16 is broken on MPS** — always use FP32 for Apple Silicon training
+- PhayaThaiBERT's 248K vocab (XLM-R-derived) requires frozen embeddings + gradient checkpointing to fit on 18GB MPS
+- Uses `offset_mapping` for tokenizer-agnostic subword-to-character alignment
+- Thai Character Cluster (TCC) boundary snapping prevents Unicode grapheme splitting during alignment
+
+## License
+
+MIT

config.json

@@ -0,0 +1,62 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "CamembertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-HARD_SKILL",
+    "2": "I-HARD_SKILL",
+    "3": "B-PERSON",
+    "4": "I-PERSON",
+    "5": "B-LOCATION",
+    "6": "I-LOCATION",
+    "7": "B-COMPENSATION",
+    "8": "I-COMPENSATION",
+    "9": "B-EMPLOYMENT_TERMS",
+    "10": "I-EMPLOYMENT_TERMS",
+    "11": "B-CONTACT",
+    "12": "I-CONTACT",
+    "13": "B-DEMOGRAPHIC",
+    "14": "I-DEMOGRAPHIC"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "B-COMPENSATION": 7,
+    "B-CONTACT": 11,
+    "B-DEMOGRAPHIC": 13,
+    "B-EMPLOYMENT_TERMS": 9,
+    "B-HARD_SKILL": 1,
+    "B-LOCATION": 5,
+    "B-PERSON": 3,
+    "I-COMPENSATION": 8,
+    "I-CONTACT": 12,
+    "I-DEMOGRAPHIC": 14,
+    "I-EMPLOYMENT_TERMS": 10,
+    "I-HARD_SKILL": 2,
+    "I-LOCATION": 6,
+    "I-PERSON": 4,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "camembert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "5.3.0",
+  "type_vocab_size": 1,
+  "use_cache": false,
+  "vocab_size": 249262
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea4fc06fbfdc121e07cb9811cf543400c2d959c9585690d8b1593d154f8bb673
+size 1107602956

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a81740837e6a4438c05e3ef1f65f8fdffdd63a81a5e01cb6df06abfbe57ee92d
+size 17048018

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED",
+    "<_>"
+  ],
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_max_length": 510,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "CamembertTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4c65168b591d533bc267f32ce96f83b12b364fbce13d9542cebeb73008b74bf
+size 5201