---
base_model:
- inflatebot/thorn-0.5
- inflatebot/thorn-0.35
- inflatebot/thorn-0.55
- inflatebot/thorn-0.45
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
![Made with NovelAI](https://huggingface.co/inflatebot/guns-and-roses-r1/resolve/main/guns%20and%20roses.png)
`Quickest draw in the West.`

A re-application of the Helium-3 process to Mistral Nemo analogues. Experimental (as you can tell by it having a revision number, I'll be playing with this more in coming time.)
Based ultimately on [Magnum-12B-V2](https://huggingface.co/anthracite-org/magnum-12b-v2) and [MN-12B-Rosier-v1](https://huggingface.co/Fizzarolli/MN-12b-Rosier-v1).

Q4 and Q6 quants available from [Reiterate3680](https://huggingface.co/Reiterate3680/guns-and-roses-r1-GGUF/tree/main) while we wait on The Usual Suspects

### Merge Method

This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [inflatebot/thorn-0.35](https://huggingface.co/inflatebot/thorn-0.35) as a base.

### Models Merged

The following models were included in the merge:
* [inflatebot/thorn-0.5](https://huggingface.co/inflatebot/thorn-0.5)
* [inflatebot/thorn-0.55](https://huggingface.co/inflatebot/thorn-0.55)
* [inflatebot/thorn-0.45](https://huggingface.co/inflatebot/thorn-0.45)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: inflatebot/thorn-0.5
  - model: inflatebot/thorn-0.45
  - model: inflatebot/thorn-0.55

merge_method: model_stock
base_model: inflatebot/thorn-0.35
dtype: bfloat16
```