This is a merge of pre-trained language models created using
mergekit.
This model was merged using the
SLERP merge method.
1base_model: OpenPipe/mistral-ft-optimized-1218
2dtype: bfloat16
3merge_method: slerp
4modules:
5 default:
6 slices:
7 - sources:
8 - layer_range: [0, 32]
9 model: OpenPipe/mistral-ft-optimized-1218
10 - layer_range: [0, 32]
11 model: mlabonne/NeuralHermes-2.5-Mistral-7B
12parameters:
13 t:
14 - filter: self_attn
15 value: [0.0, 0.5, 0.3, 0.7, 1.0]
16 - filter: mlp
17 value: [1.0, 0.5, 0.7, 0.3, 0.0]
18 - value: 0.5
