--- license: apache-2.0 base_model: Qwen/Qwen3.5-9B base_model_relation: finetune library_name: gguf pipeline_tag: text-generation language: - en tags: - cybersecurity - cve - cwe - cvss - tool-use - agent - lora - gguf - qwen3 --- # ab9b-v2 Defensive-cyber model on Qwen3.5-9B. Merged and quantised to Q4_K_M. Run the GGUF. The LoRA is here if you want the bf16 base plus the adapter instead. Trained for CVE→CWE, CVSS vectors, threat-intel questions, vulnerability review, and blue-team / DFIR / audit loops that call tools. Answers are short and lead with the conclusion. Thinking is off. ## Run ```bash huggingface-cli download dorb/ab9b-v2 ab9b-v2-Q4_K_M.gguf --local-dir . llama-server -m ab9b-v2-Q4_K_M.gguf -ngl 999 -fa on --jinja \ -c 32768 -np 1 --chat-template-kwargs '{"enable_thinking":false}' ``` OpenAI `tools` work with `--jinja`. The text protocol it was trained on is `CALL: tool_name(arg="…")` and then `FINAL: …`. The LoRA that was merged into that GGUF: ```python from transformers import AutoModelForCausalLM, AutoTokenizer from peft import PeftModel base = "Qwen/Qwen3.5-9B" model = AutoModelForCausalLM.from_pretrained(base, torch_dtype="bfloat16", device_map="auto") model = PeftModel.from_pretrained(model, "dorb/ab9b-v2", subfolder="adapters/v2a-ck900") tokenizer = AutoTokenizer.from_pretrained(base) ``` `adapters/v2b-final` and `adapters/v2c-final` are the later rounds. They were scored on the dev tier and not selected. Details are in [`evidence/REPORT.md`](evidence/REPORT.md). ## Test tier One scoring pass. Reference is `ab9b-r1` on the same base. Paired bootstrap, 95% CI. | | ab9b-v2 | ab9b-r1 | base | |---|---:|---:|---:| | cyber composite, 7 families | 0.739 | 0.725 | 0.719 | | CVE → CWE (n = 329) | 0.763 | 0.608 | | | CVSS vector (n = 334) | 0.812 | 0.715 | | | native tool-call loop, solved (n = 87) | 0.483 | 0.172 | 0.157 | | plain `CALL:` loop, solved (n = 89) | 0.528 | 0.483 | 0.236 | | single-call tool exact (n = 39) | 0.897 | 0.923 | 0.949 | | median seconds per answer | 1.89 | 3.68 | | | completion tokens per answer | 219 | 377 | | The composite move is +0.014 [−0.006, +0.033]. That misses the pre-registered +0.05 bar. The gains that clear their intervals are CVE→CWE (+0.155), CVSS (+0.097), and the native tool-call loop (+0.310). Median answer time is about half. Token count is about half. Decode speed is the same (~110 tok/s). On the same test items, against the other models that finished: wins over Cyber-Ornith-9B, Foundation-Sec-8B-Instruct, Primus-Merged-8B, SecGPT-7B, and the Qwen3.5-9B base. Ties with `ab9b-r1` and with Huihui-Qwen3.8-27B-abliterated. The 27B tie is at roughly twice the speed per quality point. Full table: [`evidence/results/league_verdict.txt`](evidence/results/league_verdict.txt). ## Training One LoRA round continued from `ab9b-r1`. r = 32, α = 32, lr 1e-4 cosine, one epoch, 1,063 steps, 16.06M tokens, 4.2 hours on one RTX 3090 (24 GB). Data is defensive: NVD CVE classification, vulnerability review, threat-intel Q&A, ATT&CK / CAPEC / CWE, analyst-brief rewrites, and oracle-checked agent episodes. Nothing from the reserved eval families. The shipped checkpoint is `v2a-ck900`. Two later rounds and two weight interpolations lost the pre-registered dev rule. `v2b` raised the agent scores and broke tool-call hygiene (it invents missing arguments). `v2c` repaired that hygiene and still scored below `v2a-ck900`, so it was never test-scored. Both adapters are in the repo so those tables can be checked. Protocol: [`evidence/GOAL.md`](evidence/GOAL.md). Numbers: [`evidence/REPORT.md`](evidence/REPORT.md). ## Files ``` ab9b-v2-Q4_K_M.gguf merged Q4_K_M, 5.8 GB adapters/v2a-ck900/ LoRA merged into the GGUF adapters/v2b-final/ later round, not selected adapters/v2c-final/ later round, not selected evidence/GOAL.md protocol, written before the test pass evidence/REPORT.md test table, league, rejected rounds evidence/results/ raw pick and verdict files SHA256SUMS GGUF and the three adapter weights ``` ## Limits Agent splits are small (89 / 87 / 39). Dev selection used 60 agent items, so a few points of noise is normal. Training families and the agent test share generators; eight reserved families were never trained on. CVE rows are the same task type as CTI-RCM and CTI-VSP, other CVEs, not the same items. Thinking mode, context past 64k, and languages other than English were not measured. The data is synthetic and defensive. It was not red-teamed. ## License Apache-2.0, same as Qwen3.5-9B. Public sources in the mix keep their own licences. ```bibtex @software{ab9b_v2_2026, title = {ab9b-v2}, author = {dorb}, year = {2026}, url = {https://huggingface.co/dorb/ab9b-v2} } ```