Calme-Ties3-78B

This model is a result of merging pre-trained language models using the TIES merge method, with prithivMLmods/Calme-Ties2-78B as the base model. The merged model includes MaziyarPanahi/calme-2.4-rys-78b, with both models contributing equally in terms of weight and density. The configuration features parameters such as normalization, int8 masking, and the use of a bfloat16 data type to enhance 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-Ties2-78B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: MaziyarPanahi/calme-2.4-rys-78b
    parameters:
      weight: 1
      density: 1
merge_method: ties
base_model: prithivMLmods/Calme-Ties2-78B
parameters:
  weight: 1
  density: 1
  normalize: true
  int8_mask: true
dtype: bfloat16
Downloads last month
4
Safetensors
Model size
78B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for prithivMLmods/Calme-Ties3-78B