Upload folder using huggingface_hub

README.md

@@ -0,0 +1,46 @@
+---
+language: en
+tags:
+  - job-classification
+  - salary-prediction
+  - experience-prediction
+  - deberta
+---
+
+# JobPredictor1
+
+Fine-tuned DeBERTa-v3-small model that predicts:
+- **Expected years of experience** required for a job
+- **Lower salary bound** (USD)
+- **Upper salary bound** (USD)
+
+## Input Format
+```
+[TITLE]: <job title> [DESC]: <job description>
+```
+
+## Outputs
+| Output | Type | Description |
+|---|---|---|
+| expected_experience_years | int | Years of experience required |
+| pay_lower | int | Lower salary bound (USD) |
+| pay_upper | int | Upper salary bound (USD) |
+
+## Normalization
+Predictions are z-score normalized. Use `norm_stats.json` to denormalize:
+```python
+real_value = pred * norm_stats[col]["std"] + norm_stats[col]["mean"]
+```
+
+## Test Set Performance
+| Metric | Value |
+|---|---|
+| Experience MAE | 0.57 years |
+| Experience Within 1yr | 83.1% |
+| Pay Lower MAE | $15,511 |
+| Pay Lower Within $20k | 84.5% |
+| Pay Upper MAE | $20,190 |
+| Pay Upper Within $20k | 76.0% |
+
+## Base Model
+microsoft/deberta-v3-small

config.json

@@ -0,0 +1,12 @@
+{
+  "base_model": "microsoft/deberta-v3-small",
+  "architecture": "DeBERTa-v3-small + 3 regression heads",
+  "outputs": {
+    "expected_experience_years": "integer (years of experience)",
+    "pay_lower": "integer (lower salary bound USD)",
+    "pay_upper": "integer (upper salary bound USD)"
+  },
+  "normalization": "z-score \u2014 use norm_stats.json to denormalize predictions",
+  "max_length": 512,
+  "dropout": 0.1
+}

norm_stats.json

@@ -0,0 +1,14 @@
+{
+  "expected_experience_years": {
+    "mean": 2.8786184883249994,
+    "std": 2.7134313236051546
+  },
+  "pay_lower": {
+    "mean": 70610.15046174698,
+    "std": 54165.983999683085
+  },
+  "pay_upper": {
+    "mean": 92701.26081987657,
+    "std": 69885.4087522144
+  }
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6890fbfd124d723db5d6baa86f519647315593c19da65d5d832b981ff808e5a8
+size 567630955

tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": [
+    "[PAD]",
+    "[CLS]",
+    "[SEP]"
+  ],
+  "is_local": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_id": 3,
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}