Community Uncensored Fine-tune of Qwen3.8-27B Trends on Hugging Face
DavidAU · hf · 2026-09-01
DavidAU released Qwen3.8-27B-TURBO-Fable-Cold-Fusion-735-882-Heretic-Uncensored-NM-DAU, a multi-stage uncensored fine-tune built on the Qwen3.5 architecture (27B, image-text-to-text pipeline). It combines community techniques like Heretic, Cold Fusion, and GAIN Training, and is currently trending on Hugging Face.
Related event: Uncensored Qwen3.8-27B Fine-tune Tops Hugging Face Trending(2 posts)→
More from Models
- Mocked benchmark shows DeepSeek's document chart grounding badly misaligned — burkov · 2026-10-18
- Dev complains Claude's habit of saying "not done" is his biggest pain point — jasonkneen · 2026-10-18
- Open-weight TYGER speech decision model makes 80ms turn-taking calls for full-duplex voice agents — solyarisoftware · 2026-10-18
- Paying Google AI subscriber blocked: custom-domain Workspace accounts can't access AI Studio — ChrisRackauckas · 2026-10-18
- Running Ling 3.1 Flash (560B MoE, 25B Active) Across 4 DGX Sparks via llama.cpp RPC — BerryBlush_Rogers691 · 2026-10-18
- Users press OpenAI on long-delayed Adult Mode a year after it was promised — ___Patrice___ · 2026-10-18