DavidAU commited on
Commit
2808fd5
·
verified ·
1 Parent(s): 1195fdf

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -8
README.md CHANGED
@@ -31,13 +31,16 @@ BRAINSTORM process was developed by David_AU.
31
 
32
  <B>What is Brainstorm?</b>
33
 
34
- The reasoning center of an LLM is taken apart, reassembled, expanded and multiplied by 5x and 10x respectively. Then these centers are individually calibrated.
35
- This process occurs at the root level - source files level. It does not use Imatrix, X-quants, Neo Class datasets and it not dependant
36
- on LLAMA.cpp per say.
 
37
 
38
- Nothing is taken away or added to the model other than what is already in the original model.
39
 
40
- The model can quanted as a GGUF, EXL2, AWQ etc etc.
 
 
41
 
42
  The core aim of this process is to increase the model's detail, concept of "world", prose quality and prose length without affecting
43
  instruction following. This will also affect any creative usage of any kind, including "brainstorming" and like case uses.
@@ -46,11 +49,9 @@ You could say this process sharpens the model's focus on it's task(s) at a deepe
46
 
47
  There are examples below showing "regular", "5x" and "10x" output below.
48
 
49
- This is experimental technology, so it might have a few "warts" and "bumps".
50
-
51
  This tech has been tested on multiple LLama2, Llama3, and Mistral models.
52
 
53
- More testing and developement is underway and there are additional sizes other than "5x" and "10x".
54
 
55
  <B>NOTES:</B>
56
 
 
31
 
32
  <B>What is Brainstorm?</b>
33
 
34
+ The reasoning center of an LLM is taken apart, reassembled, expanded and multiplied by 5x and 10x respectively.
35
+ Then these centers are individually calibrated. These "centers" also interact with each other. This introduces
36
+ subtle changes into the process. The calibrations further adjust - dial up or down - this process further. The
37
+ number of centers (5x,10x) allow even more tuning points to further customize how it reasons so to speak.
38
 
39
+ It is not in my opinion 5x or 10x "smarter" - if only that was true!
40
 
41
+ From testing it seems to ponder, and consider more carefully roughly speaking.
42
+
43
+ The process to modify the model occurs at the root level - source files level. The model can quanted as a GGUF, EXL2, AWQ etc etc.
44
 
45
  The core aim of this process is to increase the model's detail, concept of "world", prose quality and prose length without affecting
46
  instruction following. This will also affect any creative usage of any kind, including "brainstorming" and like case uses.
 
49
 
50
  There are examples below showing "regular", "5x" and "10x" output below.
51
 
 
 
52
  This tech has been tested on multiple LLama2, Llama3, and Mistral models.
53
 
54
+ More testing and development is underway and there are additional sizes other than "5x" and "10x".
55
 
56
  <B>NOTES:</B>
57