Taking the highest rated Mistral 7B from Alpaca Eval:
https://tatsu-lab.github.io/alpaca_eval/
ContextualAI/Contextual_KTO_Mistral_PairRM
and SLERP merging with the highest rated Mistral 7B from froggerics creativity rankings:
https://huggingface.co/datasets/froggeric/creativity
crestf411/daybreak-kunoichi-2dpo-7b
In testing.......
merge
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the SLERP merge method.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
slices:
- sources:
- model: crestf411/daybreak-kunoichi-2dpo-7b
layer_range: [0, 32]
- model: ContextualAI/Contextual_KTO_Mistral_PairRM
layer_range: [0, 32]
merge_method: slerp
base_model: ContextualAI/Contextual_KTO_Mistral_PairRM
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5
dtype: bfloat16