---
base_model:
- cognitivecomputations/Dolphin3.0-Mistral-24B
- baconnier/Napoleon_24B_V0.0
library_name: transformers
tags:
- mergekit
- merge

---
# merge

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

## Merge Details
### Merge Method

This model was merged using the [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using [cognitivecomputations/Dolphin3.0-Mistral-24B](https://huggingface.co/cognitivecomputations/Dolphin3.0-Mistral-24B) as a base.

### Models Merged

The following models were included in the merge:
* [baconnier/Napoleon_24B_V0.0](https://huggingface.co/baconnier/Napoleon_24B_V0.0)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: cognitivecomputations/Dolphin3.0-Mistral-24B
    parameters:
      density: 0.4
      weight: 0.6
  - model: baconnier/Napoleon_24B_V0.0
    parameters:
      density: 0.4
      weight: 0.4

merge_method: dare_ties
base_model: cognitivecomputations/Dolphin3.0-Mistral-24B

parameters:
  int8_mask: true
  normalize: true

# CORRECTED: dtype must be top-level, not under parameters
dtype: bfloat16  # Valid options: float16|bfloat16|float32

tokenizer_source: baconnier/Napoleon_24B_V0.0

```