|
--- |
|
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 |
|
 |
|
`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 |
|
|
|
Special thanks to Fizz and Toasty Pigeon. |
|
|
|
### 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 |
|
``` |
|
|