---
base_model:
- sarvamai/sarvam-m
- TheDrummer/Cydonia-24B-v3
- PocketDoc/Dans-PersonalityEngine-V1.3.0-24b
- LatitudeGames/Harbinger-24B
- aixonlab/Eurydice-24b-v3.5
library_name: transformers
tags:
- mergekit
- merge

---
# DepravedCartographer-v1.0-24b

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

## Merge Details
### Acknowledgements
Thanks to TheDrummer for his hard work on the Cydonia series of models.

### Changelog

v1.0
* Initial release. Trying only to merge Mistral 3.1 (2503) based models this time. Heavy Cydonia v3 bias.

### Merge Method

This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [TheDrummer/Cydonia-24B-v3](https://huggingface.co/TheDrummer/Cydonia-24B-v3) as a base.

### Models Merged

The following models were included in the merge:
* [sarvamai/sarvam-m](https://huggingface.co/sarvamai/sarvam-m)
* [PocketDoc/Dans-PersonalityEngine-V1.3.0-24b](https://huggingface.co/PocketDoc/Dans-PersonalityEngine-V1.3.0-24b)
* [LatitudeGames/Harbinger-24B](https://huggingface.co/LatitudeGames/Harbinger-24B)
* [aixonlab/Eurydice-24b-v3.5](https://huggingface.co/aixonlab/Eurydice-24b-v3.5)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
base_model: TheDrummer/Cydonia-24B-v3 # Cydonia v3
merge_method: model_stock
dtype: bfloat16
models:
  - model: aixonlab/Eurydice-24b-v3.5 # storytelling / RP
  - model: TheDrummer/Cydonia-24B-v3 # sprinkle in some extra Cydonia v3
  - model: PocketDoc/Dans-PersonalityEngine-V1.3.0-24b # Prompt Adherence
  - model: LatitudeGames/Harbinger-24B  # Adventure
  - model: sarvamai/sarvam-m # intelligence

```