Text Generation
Transformers
GGUF
English
mergekit
Mixture of Experts
mixture of experts
Merge
4x8B
Llama3 MOE
creative
creative writing
fiction writing
plot generation
sub-plot generation
story generation
scene continue
storytelling
fiction story
science fiction
romance
all genres
story
writing
vivid prosing
vivid writing
fiction
roleplaying
bfloat16
swearing
rp
horror
Inference Endpoints
conversational
Update README.md
Browse files
README.md
CHANGED
@@ -96,7 +96,14 @@ Example outputs below.
|
|
96 |
|
97 |
<B>Meet the Team: Mixture of Experts Models</b>
|
98 |
|
99 |
-
This model is
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
100 |
|
101 |
The mixture of experts is set at 2 experts, but you can use 3 or 4 too.
|
102 |
|
|
|
96 |
|
97 |
<B>Meet the Team: Mixture of Experts Models</b>
|
98 |
|
99 |
+
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"
|
100 |
+
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.
|
101 |
+
|
102 |
+
This model contains the four ("b3","b4","r1" and "b6") best models from this process, with the very best as a "captain" of the "MOE" so to speak.
|
103 |
+
|
104 |
+
None of these versions have ever been released, but contain the "raw source DNA" of the original model.
|
105 |
+
|
106 |
+
This process was first explored in the <a href="https://huggingface.co/collections/DavidAU/d-au-wordstorm-10-part-series-incl-full-source-67257ba027f7e244222907fd">WORDSTORM Project</a>
|
107 |
|
108 |
The mixture of experts is set at 2 experts, but you can use 3 or 4 too.
|
109 |
|