This model is the result of merging pre-trained language models using the TIES merge method, with prithivMLmods/Calme-Ties-78B serving as the base model. The merged models include MaziyarPanahi/calme-3.1-instruct-78b, with each contributing equally in terms of weight and density. The model configuration was designed with parameters like normalization, int8 masking, and a bfloat16 data type to ensure optimal performance.
This is a merge of pre-trained language models created using
mergekit.
This model was merged using the
TIES merge method using
prithivMLmods/Calme-Ties-78B as a base.
1models:
2 - model: MaziyarPanahi/calme-3.1-instruct-78b
3 parameters:
4 weight: 1
5 density: 1
6merge_method: ties
7base_model: prithivMLmods/Calme-Ties-78B
8parameters:
9 weight: 1
10 density: 1
11 normalize: true
12 int8_mask: true
13dtype: bfloat16
14
