Phi
Collection
Microsoft-based models
•
37 items
•
Updated
•
1
A model for role-play with a touch of unhinged.
This is a merge of pre-trained language models created using mergekit.
This model was merged using the SLERP merge method.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
slices:
- sources:
- model: ArliAI/Phi-3.5-mini-3.8B-ArliAI-RPMax-v1.1
layer_range: [0, 32]
- model: SicariusSicariiStuff/Phi-3.5-mini-instruct_Uncensored
layer_range: [0, 32]
merge_method: slerp
base_model: ArliAI/Phi-3.5-mini-3.8B-ArliAI-RPMax-v1.1
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