Update README.md

README.md

@@ -6,7 +6,7 @@ library_name: transformers
 tags:
 - mergekit
 - merge
-
+- not-for-all-audiences
 ---
 
 <img src="https://cdn.midjourney.com/f62c61c7-c5b4-4fa2-8d8c-ece4c65808a4/0_0.jpeg"></img>
@@ -15,6 +15,16 @@ This is a merge of pre-trained language models created using [mergekit](https://
 
 ## Merge Details
 
+WARNING: There's actually a *reason* for the not-for-all-audiences tag on this one.
+
+Qwen2.5 was much more refusal-censored in the first place compared to Mistral Nemo, but abliteration adjusts that.
+
+(It's still probably more prudish. Humanlike style points and successful instruction following aren't really a pointer away from that.)
+
+Given it's at least half-abliterated, I can't even promise it'll refuse with a guardrailed system prompt.
+
+(I suspect it will due to the healing and re-integration of the base model, but may be more jailbreakable than fully intact refusal features.)
+
 v1.1 was based on *approximately* the same steps as v1, but based on the abliterated version of Qwen-Instruct.
 
 Presuming this dealt some damage, this version heals it with the middle layers of v1.
@@ -22,6 +32,8 @@ It's still less 'refusal-censored' than v1, though be sure to calibrate the syst
 EQ-bench testing had some syntax issues still but tested at 76.1336 (with Qwen prompt that I plan on removing).
 Not too bad given at least half of it's been through abliteration and DPO.
 
+
+
 ### Merge Method
 
 This model was merged using the SLERP merge method.
@@ -47,4 +59,4 @@ parameters:
 dtype: bfloat16
 
 
-```
+```