DavidAU
/

Llama-3.2-8X3B-GATED-MOE-Reasoning-Dark-Champion-Instruct-uncensored-abliterated-18.4B-GGUF

Model card Files Files and versions Community

DavidAU commited on about 7 hours ago

Commit

36b7db9

·

verified ·

1 Parent(s): a8e7e9e

Update README.md

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -62,7 +62,8 @@ and quants have the output tensor at Q8_0, with a few choice quants at f16 (16 b
 The "gated" strucure means the "reasoning model" is re-inforced by the other 7 models in the MOE during reasoning, and then during
 output generation / non-reasoning the non-reasoning model(s) take control.
-Also, with "gating" you can directly access/control the model(s) you want to use during instruction following and generation.
 This model is the "reasoning / gated version" of this model:

 The "gated" strucure means the "reasoning model" is re-inforced by the other 7 models in the MOE during reasoning, and then during
 output generation / non-reasoning the non-reasoning model(s) take control.
+Also, with "gating" you can directly access/control the model(s) you want to use during instruction following and generation. This
+is optional - you don't need to set this to use the model normally.
 This model is the "reasoning / gated version" of this model: