qwen3.5-9b-abliterated-journalist

LoRA adapter for investigative journalism and OSINT workflows, fine-tuned from huihui-ai/Huihui-Qwen3.5-9B-abliterated.

This is the adapter checkpoint. For local inference, use the merged or GGUF variants:

• qwen3.5-9b-abliterated-journalist-merged
• qwen3.5-9b-abliterated-journalist-GGUF

Training

• Method: QLoRA with Unsloth + TRL SFT
• Base model: huihui-ai/Huihui-Qwen3.5-9B-abliterated
• Dataset: tomvaillant/investigative-journalism-training
• Task: investigative reporting assistance, OSINT methodology, verification, public-records research, source handling, and ethics

Sources And Attribution

Training examples were synthesized and curated from:

• tomvaillant/osint-tool-database, the OSINT Navigator Tool Database of 7,524 OSINT tools.
• Indicator Media briefing tools, used with permission.
• Buried Signals OSINT, Follow the Money, OPSEC, evidence grounding, Spotlight investigator, and Spotlight fact-checker skill materials.
• GIJN, Bellingcat, Verification Handbook 3, SPJ Code of Ethics, RCFP resources, and investigative manuals from UNESCO, Al Jazeera Media Institute, CiFAR, CIPE, and EJF/TEMPO Institute.
• 700 Claude Opus 4.6 synthetic instruction/response examples grounded in those materials.

Full attribution is maintained in the training repository as SOURCES.md.

Intended Use

This model is intended for journalist-facing assistant workflows: investigation planning, OSINT tool selection, verification checklists, public-source research methods, and evidence-grounded drafting. Verify model outputs before use in reporting.

This was trained with Unsloth.