DoublePivot-11b / README.md
athirdpath's picture
Create README.md
a43dc52
---
license: cc-by-nc-4.0
---
A 11b Mistral model, based on the NeverSleep recipe. Not meant for direct deployment, but who knows?
### Recipe
slices
- sources:
-
- model:
- model: maywell/PiVoT-0.1-Starling-LM-RP
-
layer_range: [0, 24]
- sources:
-
- model: maywell/PiVoT-0.1-Starling-LM-RP
-
layer_range: [8, 32]
merge_method: passthrough
dtype: bfloat16