v5.0.0: Full fine-tune on data_v10 (1.14M lines, 195 negative patterns). Fixes CloudFormation Default: FNs (F1 0.0→1.0), Redis --requirepass FNs (F1 0.67→1.0), and all 14 confirmed FP categories from real-world scanner runs. F1=0.9999, Precision=1.0000, Recall=0.9998 on held-out eval.

Updates

v4.0.0: Reduced FP on GitHub Actions SHAs, .env.example placeholders, PHP config nulls/hashids/routes, test emails, Spring annotations, DAV dates, installer curls, localhost URLs. Trained last-4-layers on data_v9 + 5608 real-world labeled examples from OWASP apps and scanner fixture repos.

v2.0.0: Retrained on data_v8 + 40k real-world labeled examples

v2.0.0: Retrained on data_v8 + 40k real-world labeled examples

Update README.md

Date update

Name update

Readme updated

Batching, GPU (CUDA), Quantization, no_grad()

addming manual batch process

Added transformer example

Updated safetensor

Model name update

Adding : library_name

Delete readme.md

Update README.md

Update README.md

Update README.md

Create README.md

Initial upload: DeBERTa secret detection model

initial commit