RDson
/

Llama-3-Magenta-Instruct-4x8B-MoE

Text Generation

Mixture of Experts

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

RDson commited on May 15

Commit

c6ab2a3

•

1 Parent(s): 72cb603

Update README.md

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -88,4 +88,5 @@ experts:
     - "inaccurate"
 gate_mode: hidden
 dtype: float16
-```

     - "inaccurate"
 gate_mode: hidden
 dtype: float16
+```
+Some inspiration for the Mergekit yaml file is from [LoneStriker/Umbra-MoE-4x10.7-2.4bpw-h6-exl2](https://huggingface.co/LoneStriker/Umbra-MoE-4x10.7-2.4bpw-h6-exl2).