Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more
Container

Run this model inference with full control and performance in your environment.

Learn more

Get help setting up a custom Dedicated Endpoints.

Talk with our engineer to get a quote for reserved GPU instances with discounts.

README

License: apache-2.0

Results: base vs v2 vs v3 (real-defect eval, n=32)

MetricBasev2v3
Verdict accuracy~72%78.1%78.1%
Positive recall87.5% (14/16)56.2% (9/16)62.5% (10/16)
Negative specificity~56%100%93.8%
Category match56.2%43.8%43.8%
Invalid JSON0/320/320/32

Training data

v2's 498 rows + 14 access/logic-bypass contrastive pairs (gen_bypass_pairs.py, Drupal-expert-verified) = 526 rows. QLoRA r=16 on q/k/v/o, batch4+grad-ckpt, MAX_LEN=2048, 3 epochs, lr 2e-4. Full 3-way report with per-item detail ships in the project repo under docs/eval/dcr-qlora-v3-report.md.

Limitations

Same as v2, plus: v3 traded v2's 100% specificity for one false positive without a real recall gain, so it is not a recommended upgrade over v2. Real-defect recall remains ~60%; the access-bypass class is still largely missed. Keep a human in the loop; the model is one component of a hybrid pipeline (static analyzers + RAG + this adapter).

Model provider

bartek-flp

Model tree

Base

Qwen/Qwen3-Coder-30B-A3B-Instruct

Adapter

this model

Modalities

Input

Text

Output

Text

Pricing

Dedicated Endpoints

View details

Supported Functionality

Model APIs

Dedicated Endpoints

Container

More information

Explore FriendliAI today