Copied the merge script from
tannedbum/L3-Nymeria-8B and made it use
Casual-Autopsy/L3-Umbral-Mind-RP-v1.0-8B as the base model instead.
This is a merge of pre-trained language models created using
mergekit.
This model was merged using the SLERP merge method.
1
2slices:
3 - sources:
4 - model: Casual-Autopsy/L3-Umbral-Mind-RP-v1.0-8B
5 layer_range: [0, 32]
6 - model: princeton-nlp/Llama-3-Instruct-8B-SimPO
7 layer_range: [0, 32]
8merge_method: slerp
9base_model: Casual-Autopsy/L3-Umbral-Mind-RP-v1.0-8B
10parameters:
11 t:
12 - filter: self_attn
13 value: [0.4, 0.5, 0.6, 0.4, 0.6]
14 - filter: mlp
15 value: [0.6, 0.5, 0.4, 0.6, 0.4]
16 - value: 0.5
17dtype: bfloat16
18
