Slerp Merge of cookinai/CatMacaroni-Slerp and EmbeddedLLM/Mistral-7B-Merge-14-v0.2
.yaml file for mergekit
slices:
- sources:
- model: EmbeddedLLM/Mistral-7B-Merge-14-v0.2
layer_range: [0, 32]
- model: cookinai/CatMacaroni-Slerp
layer_range: [0, 32]
merge_method: slerp
base_model: EmbeddedLLM/Mistral-7B-Merge-14-v0.2
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 # fallback for rest of tensors
dtype: bfloat16