redaihf/goetia13_frankenmerge_sample
Viewer • Updated • 34 • 8 • 1
Red (HF)
redaihf
AI & ML interests
(SO)MPOA decensoring, residual refusals, contextual ethical realignment
Recent Activity
reacted to BoldingBuilds's post with 🔥 1 minute ago
Abliterated thinking models have a habit: they decide what to say, then keep arguing with themselves until the token budget runs out. Qwen3.8-27B Abliterated ThinkFix is an uncensored Qwen3.8-27B with one output row edited so the model closes its thinking when it's ready to answer.
On 40 sensitive prompts the edit never saw, 8k output cap: 33 replies finished cleanly instead of 22, 5 hit the limit instead of 17, 61 minutes for the set instead of 75.
Agent use was checked four ways and the edit changes nothing there. MTP draft head kept. Q4_K_M to Q8_0, each tested after the edit. The card lists what the edit was fit on and what it does not do.
https://huggingface.co/BoldingBuilds/Qwen3.8-27B-Abliterated-ThinkFix-GGUF new activity 30 minutes ago
mradermacher/model_requests:🌊 DeepWater Pleroma 24B new activity about 19 hours ago
Blackroot/Ammeg-26B-A4:UnevenOrganizations
