GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
tomvaillant
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
tomvaillant
Model Tree
Base
huihui-ai/Huihui-Qwen3.6-27B-abliterated
Adapter
this model
Input Modalities
Text
Image
Video
Output Modalities
Text
Supported Functionality
Dedicated Endpoints
FastModel + TRL SFT, following the official Unsloth Qwen3.5 fine-tune recipe (canonical for Qwen3.6 too).huihui-ai/Huihui-Qwen3.6-27B-abliterated (multimodal, hybrid-thinking, dense 27B, qwen3_5 architecture)tomvaillant/investigative-journalism-training (687 examples, OSINT methodology)bias="none"; use_gradient_checkpointing="unsloth"load_in_16bit=True; 4-bit QLoRA explicitly not recommended for Qwen3.5/3.6 per Unsloth docs)finetune_vision_layers=False) — text-only LoRA, vision capability preserved byte-identical to baseTraining data: tomvaillant/investigative-journalism-training — 687 instruction/response pairs synthesized by Claude Opus 4.6 (Anthropic) from the Buried Signals OSINT and investigative-journalism corpus: OSINT Navigator tool data, Indicator Media briefings, Buried Signals investigative skills, GIJN, Bellingcat, Verification Handbook 3, SPJ Code of Ethics, RCFP, and public manuals from UNESCO, Al Jazeera Media Institute, CiFAR, CIPE, and EJF/TEMPO Institute.
See the dataset card for the full source list, licenses, and per-partner attribution.
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.