|
|
|
--- |
|
|
|
base_model: |
|
- nothingiisreal/MN-12B-Celeste-V1.9 |
|
- intervitens/mini-magnum-12b-v1.1 |
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
license: apache-2.0 |
|
|
|
--- |
|
|
|
![](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ) |
|
|
|
# QuantFactory/MN-12B-Starcannon-v2-GGUF |
|
This is quantized version of [aetherwiing/MN-12B-Starcannon-v2](https://huggingface.co/aetherwiing/MN-12B-Starcannon-v2) created using llama.cpp |
|
|
|
# Original Model Card |
|
|
|
# MN-12B-Starcannon-v2 |
|
|
|
> A star and a gun is all you need |
|
|
|
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). Turned out to be a bit more Magnum-esque, but still is very creative, and writing style is pretty nice, even if some slop words appear time to time. Might be a good fit for people wanting more variety than Magnum has, and more verbose prose than Celeste v1.9 has. |
|
<br><br> |
|
[Dynamic FP8](https://huggingface.co/aetherwiing/MN-12B-Starcannon-v2-fp8-dynamic) <br> |
|
[Static GGUF (by Mradermacher)](https://huggingface.co/mradermacher/MN-12B-Starcannon-v2-GGUF) <br> |
|
[EXL2 (by kingbri of RoyalLab)](https://huggingface.co/royallab/MN-12B-Starcannon-v2-exl2) |
|
## Merge Details |
|
### Merge Method |
|
|
|
This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [nothingiisreal/MN-12B-Celeste-V1.9](https://huggingface.co/nothingiisreal/MN-12B-Celeste-V1.9) as a base. |
|
|
|
### Merge fodder |
|
|
|
The following models were included in the merge: |
|
* [nothingiisreal/MN-12B-Celeste-V1.9](https://huggingface.co/nothingiisreal/MN-12B-Celeste-V1.9) |
|
* [intervitens/mini-magnum-12b-v1.1](https://huggingface.co/intervitens/mini-magnum-12b-v1.1) |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
models: |
|
- model: intervitens/mini-magnum-12b-v1.1 |
|
parameters: |
|
density: 0.3 |
|
weight: 0.5 |
|
- model: nothingiisreal/MN-12B-Celeste-V1.9 |
|
parameters: |
|
density: 0.7 |
|
weight: 0.5 |
|
|
|
merge_method: ties |
|
base_model: nothingiisreal/MN-12B-Celeste-V1.9 |
|
parameters: |
|
normalize: true |
|
int8_mask: true |
|
dtype: bfloat16 |
|
|
|
``` |
|
|