SteelStorage
/

Lumosia-MoE-4x10.7

Text Generation

Mixture of Experts

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Steelskull commited on Jan 22

Commit

0561aa7

•

1 Parent(s): b60b10d

Update README.md

Files changed (1) hide show

README.md +6 -3

README.md CHANGED Viewed

@@ -21,7 +21,7 @@ This is a very experimantal model. its a MoE of all good performing Solar models
 Why? Dunno whated to see what would happen
-context is maybe 16k?
 Chat-instruct breaks the model at the moment, not really sure why, even tho it will follow instructions.
@@ -31,9 +31,12 @@ https://huggingface.co/TheBloke/Lumosia-MoE-4x10.7-GGUF
 https://huggingface.co/TheBloke/Lumosia-MoE-4x10.7-GPTQ
-Update: (In Progress)
-Lumosia v1.5 will have the the same MoE models but with a fully trained head and gates. Sould increase performance alot.
 Template: ChatML
 ```

 Why? Dunno whated to see what would happen
+context is 4k but coherent up to 16k
 Chat-instruct breaks the model at the moment, not really sure why, even tho it will follow instructions.
 https://huggingface.co/TheBloke/Lumosia-MoE-4x10.7-GPTQ
+Update: (Done)
+Lumosia v1.5 has been uploaded.
+Update 2:
+A Lumosia Personality tavern card has been added
 Template: ChatML
 ```