---
base_model:
- prithivMLmods/Calme-Ties2-78B
- MaziyarPanahi/calme-2.4-rys-78b
library_name: transformers
tags:
- mergekit
- merge

---
# **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](https://github.com/cg123/mergekit).

# **Merge Method**

This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [prithivMLmods/Calme-Ties2-78B](https://huggingface.co/prithivMLmods/Calme-Ties2-78B) as a base.

# **Models Merged**

The following models were included in the merge:
* [MaziyarPanahi/calme-2.4-rys-78b](https://huggingface.co/MaziyarPanahi/calme-2.4-rys-78b)

# **Configuration**

The following YAML configuration was used to produce this model:

```yaml
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

```