DavidAU commited on
Commit
edd5542
·
verified ·
1 Parent(s): 926db09

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -3
README.md CHANGED
@@ -21,8 +21,10 @@ NOTE: Links to GGUFs below.
21
 
22
  <B>Evolved "Dark Planet" Model X 8</B>
23
 
24
- This model is based on the original "Llama 3 Dark Planet 8B" (<a href="https://huggingface.co/DavidAU/L3-Dark-Planet-8B-GGUF">GGUF</a> / <a href="https://huggingface.co/DavidAU/L3-Dark-Planet-8B">SOURCE</a>) merge that has been "evolved" several times. Each "evolved"
25
- version is then tested, if it is unique and/or removes certain negative attibutes and/or enhances certain positive attibutes, it is kept otherwise it is deleted.
 
 
26
 
27
  This model contains the eight best models from this process, with the very best as a "captain" of the "MOE" so to speak.
28
 
@@ -36,6 +38,12 @@ When all eight of these are activated...
36
 
37
  I have included 3 example generations at the bottom of this page with varying level of "experts" used.
38
 
 
 
 
 
 
 
39
  SIDE NOTE:
40
 
41
  Uusually a "MOE" is constructed with different models, to give the "moe model" some of the best of each (or not) during generation.
@@ -130,7 +138,7 @@ IMATRIX GGUFS:
130
 
131
  <B>Warning: Romance, Drama, Horror, Cursing, Gore, Intense - NOT for all audiences.</B>
132
 
133
- EXAMPLE GENERATIONS for "L3-MOE-8X8B-Dark-Planet-8D-Mirrored-Chaos-47B":
134
 
135
  Q2K GGUF - (lowest quality quant) - this will be your lowest quality output.
136
 
 
21
 
22
  <B>Evolved "Dark Planet" Model X 8</B>
23
 
24
+ This model is based on the original "Llama 3 Dark Planet 8B" (<a href="https://huggingface.co/DavidAU/L3-Dark-Planet-8B-GGUF">GGUF</a> /
25
+ <a href="https://huggingface.co/DavidAU/L3-Dark-Planet-8B">SOURCE</a>) merge that has been "evolved" several times. Each "evolved"
26
+ version is then tested, if it is unique and/or removes certain negative attibutes and/or enhances certain positive attibutes,
27
+ it is kept otherwise it is deleted.
28
 
29
  This model contains the eight best models from this process, with the very best as a "captain" of the "MOE" so to speak.
30
 
 
38
 
39
  I have included 3 example generations at the bottom of this page with varying level of "experts" used.
40
 
41
+ In addition model:
42
+
43
+ [ https://huggingface.co/aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored ]
44
+
45
+ Was used to in a merge with the "Captain" of the MOE to both decensor the model more, and give it 128k context.
46
+
47
  SIDE NOTE:
48
 
49
  Uusually a "MOE" is constructed with different models, to give the "moe model" some of the best of each (or not) during generation.
 
138
 
139
  <B>Warning: Romance, Drama, Horror, Cursing, Gore, Intense - NOT for all audiences.</B>
140
 
141
+ EXAMPLE GENERATIONS for "L3.1-MOE-8X8B-Dark-Planet-8D-Mirrored-Chaos-Uncensored-47B":
142
 
143
  Q2K GGUF - (lowest quality quant) - this will be your lowest quality output.
144