morikomorizz commited on
Commit
2dd055d
·
1 Parent(s): 1e3f380

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -19,6 +19,7 @@ tags:
19
  27B reasoning powerhouse built on the Qwen3.6 architecture. Primal takes the already-impressive base and strips away the overcautious refusal behavior that tends to get in the way of real, complex work.
20
 
21
  The goal is to create a model that does not judge or label its users, while maintaining the model’s ability to think and serve users.
 
22
  ---
23
 
24
  ## What's Different
@@ -26,6 +27,7 @@ The goal is to create a model that does not judge or label its users, while main
26
  The refusal circuits were surgically targeted across **layers 19–46**
27
  - Refusals dropped from **91/100 to 6/100**
28
  - KL divergence : **0.0678**
 
29
  ---
30
 
31
  ## Usage
 
19
  27B reasoning powerhouse built on the Qwen3.6 architecture. Primal takes the already-impressive base and strips away the overcautious refusal behavior that tends to get in the way of real, complex work.
20
 
21
  The goal is to create a model that does not judge or label its users, while maintaining the model’s ability to think and serve users.
22
+
23
  ---
24
 
25
  ## What's Different
 
27
  The refusal circuits were surgically targeted across **layers 19–46**
28
  - Refusals dropped from **91/100 to 6/100**
29
  - KL divergence : **0.0678**
30
+ -
31
  ---
32
 
33
  ## Usage