GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
bartek-flp
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
bartek-flp
Model Tree
Qwen/Qwen3-Coder-30B-A3B-Instruct
Input Modalities
Output Modalities
Supported Functionality
| Metric | Base | v2 | v3 |
|---|---|---|---|
| Verdict accuracy | ~72% | 78.1% | 78.1% |
| Positive recall | 87.5% (14/16) | 56.2% (9/16) | 62.5% (10/16) |
| Negative specificity | ~56% | 100% | 93.8% |
| Category match | 56.2% | 43.8% | 43.8% |
| Invalid JSON | 0/32 | 0/32 | 0/32 |
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.
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).