Calme-Ties2-78B

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.

Merge

This is a merge of pre-trained language models created using mergekit.

Merge Method

This model was merged using the TIES merge method using prithivMLmods/Calme-Ties-78B as a base.

Models Merged

The following models were included in the merge:

• MaziyarPanahi/calme-3.1-instruct-78b

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: MaziyarPanahi/calme-3.1-instruct-78b
    parameters:
      weight: 1
      density: 1
merge_method: ties
base_model: prithivMLmods/Calme-Ties-78B
parameters:
  weight: 1
  density: 1
  normalize: true
  int8_mask: true
dtype: bfloat16