From 817aeb9232eefcd3f942fa79602c30a58544a102 Mon Sep 17 00:00:00 2001 From: Atlas Date: Sun, 5 Apr 2026 00:41:47 -0700 Subject: [PATCH] Auto-summarize: Testing Abliterated Models Performance and Training Effects.md --- ...rated Models Performance and Training Effects.md | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/Testing Abliterated Models Performance and Training Effects.md b/Testing Abliterated Models Performance and Training Effects.md index 9fb12ee..9d7f1bf 100644 --- a/Testing Abliterated Models Performance and Training Effects.md +++ b/Testing Abliterated Models Performance and Training Effects.md @@ -1,3 +1,16 @@ +--- +created: '2026-04-05T05:39:22+00:00' +id: ac34ef61-c715-432a-be39-5e3df4cd701b +links: [] +modified: '2026-04-05T05:39:22+00:00' +summary: Abliterated models typically show performance degradation, but fine-tuning + after abliteration can recover performance and create uncensored models that rival + or outperform originals, as demonstrated by mradermacher/Qwen3-30B-A3B-abliterated-erotic-i1-GGUF + and mlabonne/NeuralDaredevil-8B-abliterated. +tags: [] +title: Testing Abliterated Models Performance and Training Effects +--- + 9/26/25 #AI #MachineLearning #ModelTesting #Abliteration #FineTuning #Qwen3 #Llama3 #UncensoredModels