JobLink Semantic Match Scorer
DeBERTa-v3-base fine-tuned for the JobLink platform.
Predicts a continuous match score [0.0 – 1.0] between a job description and a candidate CV.
Usage
from transformers import pipeline
pipe = pipeline("text-classification", model="abnetsisaynew/joblink-match-scorer", function_to_apply="none")
score = pipe("JOB: <job_text> [SEP] CANDIDATE: <cv_text>")[0]["score"]
Test-Set Results
| Metric | Value | Target |
|---|---|---|
| RMSE | 0.0920 | lower |
| MAE | 0.0761 | lower |
| F1 | 0.9426 | ≥ 0.85 |
| Precision | 0.9208 | ≥ 0.80 |
| Recall | 0.9654 | ≥ 0.90 |
RAD Compliance: 🟢 PASSED
- Downloads last month
- 33