metadata
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- RatanRohith/NeuralPizza-7B-V0.1
- PetroGPT/WestSeverus-7B-DPO
NeuralPizza-WestSeverus-7B-Merge-slerp
NeuralPizza-WestSeverus-7B-Merge-slerp is a merge of the following models using mergekit:
🧩 Configuration
slices:
- sources:
- model: RatanRohith/NeuralPizza-7B-V0.1
layer_range: [0, 32]
- model: PetroGPT/WestSeverus-7B-DPO
layer_range: [0, 32]
merge_method: slerp
base_model: PetroGPT/WestSeverus-7B-DPO
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