Good Imagination
Collection
4 items
•
Updated
•
1
This is a merge of pre-trained language models created using mergekit.
This model was merged using the SLERP merge method.
The following models were included in the merge:
The following YAML configuration was used to produce this model:
slices:
- sources:
- model: jaspionjader/fr-18-8b
layer_range:
- 0
- 32
- model: jaspionjader/Kosmos-EVAA-Franken-v38-8B
layer_range:
- 0
- 32
merge_method: slerp
base_model: jaspionjader/fr-18-8b
parameters:
t:
- filter: self_attn
value:
- 0.22
- 0.23
- 0.21
- 0.24
- 0.23
- filter: mlp
value:
- 0.23
- 0.22
- 0.24
- 0.21
- 0.22
- value: 0.33
dtype: bfloat16