Cerebral-Infinity-7B
The concept behind this merge is to create a "smarter" RP model, based on the already great InfinityRP, with the added logical reasoning qualities of Cerebrum.
I believe it has achieved that based on testing I did, however it may still offer refusals, but they are easy to work around with character cards and good prompting.
Merge Details
This is a merge of pre-trained language models created using mergekit.
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: Endevor/InfinityRP-v1-7B
layer_range: [0, 32]
- model: AetherResearch/Cerebrum-1.0-7b
layer_range: [0, 32]
merge_method: slerp
base_model: Endevor/InfinityRP-v1-7B
parameters:
t:
- filter: self_attn
value: [0.7, 0.3, 0.6, 0.2, 0.5]
- filter: mlp
value: [0.3, 0.7, 0.4, 0.8, 0.5]
- value: 0.5
dtype: bfloat16