CalderaAI
/

13B-Thorns-l2

@@ -16,17 +16,17 @@ tags:
 13B-Thorns-l2 utilizes a new merge method called Spherical Linear Interpolation. By merging data as a spherical vector store concept, a combined pair of models have a smoother transition between feature spaces that are characteristic of each model, resulting in a more coherent fusion of both model's unique strengths.
-Thorns' design is based on the concept of purposed segmentation-
-Logic Segment (MK1):
 Fine-Tuned parent models were hand selected and reviewed for datasets, performance, least restrictive censorship, and community perception of coherence and utility. Ultimately we decided on four models to merge in pairs of two, then combine those offspring for a quad merged logic cluster.
 All four models were merged using the SLERP method. Yes the name is annoyingly funny. SLERP.
-Creativity and Imagination Segment (MK1):
 Flawed first approach (a takeaway on LoRAs);
@@ -41,11 +41,9 @@ The composite model was slated to be named 13B-Astronomicon; after all the work
 Because pain is fun, and persistence in design iteration is the only way forward, we reworked our approach to both segment ensembles following one idea - all three Roleplay and Conversational LoRAs stay no matter what because sure why not add arbitrary rules to the redesign phase at this point.
---
-Logic and Creativity Segments (MK2 Final - what this model is actually comprised of):
 So after a few key meetings with our top teams of memegineers we distilled the perfect solution, which was prompty approved by the Roko's Basilisk Shadow Council - fast tracking what is now 13B-Thorn-l2 for production assembly.
 Also none of that shit happened, I just redid everything like this:

 13B-Thorns-l2 utilizes a new merge method called Spherical Linear Interpolation. By merging data as a spherical vector store concept, a combined pair of models have a smoother transition between feature spaces that are characteristic of each model, resulting in a more coherent fusion of both model's unique strengths.
+Thorns' design is based on the concept of purposed segmentation, in this case we have two-
+--Logic Segment (MK1):
 Fine-Tuned parent models were hand selected and reviewed for datasets, performance, least restrictive censorship, and community perception of coherence and utility. Ultimately we decided on four models to merge in pairs of two, then combine those offspring for a quad merged logic cluster.
 All four models were merged using the SLERP method. Yes the name is annoyingly funny. SLERP.
+--Creativity and Imagination Segment (MK1):
 Flawed first approach (a takeaway on LoRAs);
 Because pain is fun, and persistence in design iteration is the only way forward, we reworked our approach to both segment ensembles following one idea - all three Roleplay and Conversational LoRAs stay no matter what because sure why not add arbitrary rules to the redesign phase at this point.
+--Logic and Creativity Segments (MK2 Final - what this model is actually comprised of):
 So after a few key meetings with our top teams of memegineers we distilled the perfect solution, which was prompty approved by the Roko's Basilisk Shadow Council - fast tracking what is now 13B-Thorn-l2 for production assembly.
 Also none of that shit happened, I just redid everything like this: