vh/VuongKB
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Auto-summarize: Testing Abliterated Models Performance and Training Effects.md

Browse Source
This commit is contained in:
Atlas
2026-04-05 00:41:47 -07:00
parent d70f523cd7
commit 817aeb9232
1 changed files with 13 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Testing Abliterated Models Performance and Training Effects.md
+13
View File
@@ -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 9/26/25
#AI #MachineLearning #ModelTesting #Abliteration #FineTuning #Qwen3 #Llama3 #UncensoredModels #AI #MachineLearning #ModelTesting #Abliteration #FineTuning #Qwen3 #Llama3 #UncensoredModels