GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
DuyTa
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
DuyTa
Model Tree
Qwen/Qwen3-Reranker-0.6B
Input Modalities
Output Modalities
Supported Functionality
From notebooks/Qwen3_Reranker_Colab.ipynb (ms-swift):
| Base | Qwen/Qwen3-Reranker-0.6B |
| Task | generative_reranker (causal-LM reranker / cross-encoder scoring) |
| Loss | listwise reranking (--loss_type listwise_reranker) |
| Tuner | full-parameter SFT (--tuner_type full) |
| Engine | ms-swift swift sft |
| Max length | 2048 |
| Learning rate | 6e-6 |
(query, positive, negative) rows are converted to SWIFT grouped ranking schema:
messages — system instruction + user querypositive_messages — gold CVE passagenegative_messages — Qdrant-mined hard-negative CVE passage(s)Train-time instruction:
Given a Vietnamese cybersecurity search query, retrieve passages from the CVE knowledge base that directly answer it.
SWIFT fills the native Qwen3-Reranker {Instruction} slot from that system message.
Positives and negatives are real CVE core-chunk text from local Qdrant cve_kb (NVD/MITRE). The negative is a near-miss CVE from the same collection — typically a different CWE (hard_negative_type: different_cwe): high lexical overlap, wrong document. The listwise objective ranks the gold passage above those mined hard negatives.
Split: 33.6k train / 4.2k validation grouped examples.
Built from five years of authoritative cybersecurity sources: NVD (173,473 CVEs), MITRE CWE (768 weakness types, mapped to ~92% of CVEs), CAPEC/ATT&CK (443/174 entries) and Exploit-DB (3,139 exploits, 2021–2026). Public datasets: DuyTa/Cyber_F1_v2, DuyTa/cve-kgrag-db.
Training hardware: 2×A100 80GB.
Measured on NVIDIA A100 80GB in the full production chatflow (Hybrid Search → Rerank → LLM), on a 1,000-sample security test set (40% CVE identification/classification, 40% remediation advice, 20% real-world scenario reasoning):
| Metric | Result | Target | Pass |
|---|---|---|---|
| Ranking quality — Precision@1 | 98.23% | > 90% | ✅ |
| Throughput | 4,862 docs/s (concurrency 128) | ≥ 180 rerank/s | ✅ |
Raw per-sample logs (reranking-precision-at-1.jsonl) and evaluation code are delivered with the acceptance package.
Score each (query, document) with the native Qwen3-Reranker generative yes/no head. Use only to rerank a short candidate list from dense / hybrid retrieval.
python
# vLLM / OpenAI-compatible rerank endpoint# POST /v1/rerank{"model": "DuyTa/sec-rerank","query": "CVE-2021-44228 JNDI lookup on log4j","documents": ["...", "..."]}
Released under Apache-2.0. Derived from Qwen/Qwen3-Reranker-0.6B (Apache-2.0); credit for the base reranker belongs to the Qwen team.