DavidAU
/

Mistral-MOE-4X7B-Dark-MultiVerse-Uncensored-Enhanced32-24B-gguf

Text Generation

mixture of experts

Mixture of Experts

32 bit enhanced

float 32 quants

creative writing

fiction writing

plot generation

sub-plot generation

story generation

science fiction

Inference Endpoints

Model card Files Files and versions Community

DavidAU commited on 17 days ago

Commit

87cf491

·

verified ·

1 Parent(s): e91af89

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -45,7 +45,7 @@ pipeline_tag: text-generation
 <I><small> A float 32 high precision M.O.E model, quanted in float 32 with additional upgraded and augmented quants too. </small></i>
-<img src="dark-m.jpg" style="float:right; width:300px; height:300px; padding:10px;">
 It is a Mistral model, max context of 32k (32768) using mixture of experts to combine FOUR top Mistral 7B
 models into one massive powerhouse at 24B parameters (equal to 28B - 4 X 7 B).

 <I><small> A float 32 high precision M.O.E model, quanted in float 32 with additional upgraded and augmented quants too. </small></i>
+<img src="dark-mv-32.jpg" style="float:right; width:300px; height:300px; padding:10px;">
 It is a Mistral model, max context of 32k (32768) using mixture of experts to combine FOUR top Mistral 7B
 models into one massive powerhouse at 24B parameters (equal to 28B - 4 X 7 B).