This is a merge of pre-trained language models created using
mergekit.
This model was merged using the SLERP merge method.
1
2merge_method: slerp
3base_model: chanwit/flux-7b-base-stage-00
4slices:
5 - sources:
6 - model: chanwit/flux-7b-base-stage-00
7 layer_range: [0, 32]
8 - model: Intel/neural-chat-7b-v3-3
9 layer_range: [0, 32]
10parameters:
11 t:
12 - filter: self_attn
13 value: [0, 0.5, 0.3, 0.7, 1]
14 - filter: mlp
15 value: [1, 0.5, 0.7, 0.3, 0]
16 - value: 0.5 # fallback for rest of tensors
17dtype: bfloat16
18
