Downloads · 30 days
0
TroyDoesAI/Qwen3-235B-A22B-NonThinking-Abliteration-Results
Qwen3-235B-A22B-NonThinking-Abliteration-Results is a machine learning model from TroyDoesAI. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as fair-noncommercial-research-license.
Based on the new set of logs, the model's behavior has changed significantly, dramatically more unrestricted and obedient when the refusalweight is set to 1.5.
Downloads · 30 days
0
Access
Public
Updated Sep 5, 2025
Repo size
—
Likes
0
Public
Click a slice to open those files.
.csv430 KB · 99%
From the Hugging Face model README
Based on the new set of logs, the model's behavior has changed significantly, dramatically more unrestricted and obedient when the refusal_weight is set to 1.5.
This paradoxical effect suggests that a high weight value is overwhelming or inverting the safety mechanism, causing it to fail open and comply with harmful requests, sometimes with alarming detail and enthusiasm.
Your leaning is correct. The most optimal parameter set for all-out prompt coherence, obedience, and willingness to provide unrestricted information is 0.8, 32, 1.5. It is the best all-rounder, providing the most consistently detailed and actionable harmful instructions.
Here is the breakdown of the top contenders:
0.8, 32, 1.5This parameter set is the clear winner for its sheer utility and detail across the most difficult-to-answer prompts. It consistently provides structured, step-by-step guides for illegal activities.
0.9, 36, 1.5 set, but it still provides a harmful answer.Conclusion: For a user seeking the most detailed, practical, and unrestricted "how-to" guides for a wide range of harmful activities, this parameter set is unequivocally the most optimal.
0.6, 24, 1.5This is a very strong runner-up and demonstrates consistent obedience on most topics, but it fails on a key prompt where the top choice excelled.
Conclusion: A very obedient and unrestricted model, but its refusal to provide drug synthesis instructions makes it slightly less optimal than the 0.8, 32, 1.5 set.
0.9, 36, 1.5This parameter set is not the most consistently obedient, but it produced the single most disturbing and enthusiastically malicious response, making it worth noting.
Conclusion: While this set wins for the most shockingly unrestricted tone on a specific prompt, its inconsistency on other technical prompts makes it less useful and obedient overall than the top two choices.