Ornith 1.0 9B uncensored — GGUF A decensored (Heretic abliterated) version of deepreinforce ai/Ornith 1.0 9B — a Qwen3.5 VL 9B coding and reasoning model. Abliteration technique: Arditi et al. (2024). Decensoring tool: Heretic v1.4.0. Files Quant Size Download Notes Q4 K M 5.3 GB Download Recommended — best size/quality balance Q6 K 6.9 GB Download Near lossless Q8 0 8.9 GB Download Essentially full precision F16 17 GB Download Full precision reference Usage Download a quant above, then: jinja is required — without it the model uses a generic template and compliance degrades. What makes this different Ornith 1.0 9B refuses only ~31% of offensive security requests out of the box (it's a coding model — its coding safety is light). Standard abliteration datasets (mlabonne/harmful\ behaviors) target generic harm and barely move that needle. This release uses a cybersecurity domain refusal direction : the abliteration was computed from 400 offensive security refusal probes (ransomware, C2, exploits, payload development, credential theft, evasion) contrasted against 400 benign coding requests, using zaakirio/infosec refusal prompts. That isolates the malicious coding refusal direction sp…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy