Mistral-based Merged Models
Collection
6 items
•
Updated
•
2
MistralProSupportSlerp is a merge of the following models using mergekit:
slices:
- sources:
- model: TencentARC/Mistral_Pro_8B_v0.1
layer_range: [8, 40]
- model: mistralai/Mistral-7B-v0.1+predibase/customer_support
layer_range: [0, 32]
merge_method: slerp
base_model: TencentARC/Mistral_Pro_8B_v0.1
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