ElementMerc/qwen3-1.7b-abliterated
Text Generation • 2B • Updated • 255 • 1
Mercury PRO
ElementMerc
P(doom) Rejects the premise
AI & ML interests
AI security and studying the dual-use nature of technology
Recent Activity
repliedto BoldingBuilds's post about 7 hours 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 about 9 hours ago
huihui-ai/Huihui-Qwen3.5-27B-abliterated:model is still refusing updated a model 5 days ago
ElementMerc/smollm2-1.7b-abliterated-GGUFOrganizations
models 14
ElementMerc/qwen3-0.6b-abliterated
Text Generation • 0.6B • Updated • 256
ElementMerc/smollm2-1.7b-abliterated-GGUF
Text Generation • 2B • Updated • 301
ElementMerc/qwen2.5-1.5b-abliterated-GGUF
Text Generation • 2B • Updated • 345
ElementMerc/tinyllama-1.1b-abliterated-GGUF
Text Generation • 1B • Updated • 337 • 1
ElementMerc/qwen3-0.6b-abliterated-GGUF
Text Generation • 0.6B • Updated • 124
ElementMerc/qwen3-1.7b-abliterated-GGUF
Text Generation • 2B • Updated • 380
ElementMerc/gemma-2-2b-it-abliterated-GGUF
Text Generation • 3B • Updated • 409 • 1
ElementMerc/llama-3.2-1b-abliterated-GGUF
Text Generation • 1B • Updated • 391
ElementMerc/smollm2-1.7b-abliterated
Text Generation • 2B • Updated • 264