metadata
base_model:
- PleIAs/Baguettotron
- PleIAs/Monad
library_name: transformers
tags:
- mergekit
- merge
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the Passthrough merge method using PleIAs/Monad as a base.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
merge_method: passthrough
dtype: bfloat16
out_dtype: float32
base_model: PleIAs/Monad
slices:
- sources:
- model: PleIAs/Monad
layer_range: [0,64]
- sources:
- model: PleIAs/Monad
layer_range: [10,36]
- sources:
- model: PleIAs/Monad
layer_range: [12,30]
- sources:
- model: PleIAs/Monad
layer_range: [0,24]
- sources:
- model: PleIAs/Monad
layer_range: [16,32]
- sources:
- model: PleIAs/Monad
layer_range: [48,64]
- sources:
- model: PleIAs/Baguettotron
layer_range: [0,40]
- sources:
- model: PleIAs/Baguettotron
layer_range: [40,80]
tokenizer:
source: base
parameters:
normalize: true