Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
|
| 4 |
+
base_model:
|
| 5 |
+
- nothingiisreal/MN-12B-Celeste-V1.9
|
| 6 |
+
- intervitens/mini-magnum-12b-v1.1
|
| 7 |
+
library_name: transformers
|
| 8 |
+
tags:
|
| 9 |
+
- mergekit
|
| 10 |
+
- merge
|
| 11 |
+
license: apache-2.0
|
| 12 |
+
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
# QuantFactory/MN-12B-Starcannon-v2-GGUF
|
| 18 |
+
This is quantized version of [aetherwiing/MN-12B-Starcannon-v2](https://huggingface.co/aetherwiing/MN-12B-Starcannon-v2) created using llama.cpp
|
| 19 |
+
|
| 20 |
+
# Original Model Card
|
| 21 |
+
|
| 22 |
+
# MN-12B-Starcannon-v2
|
| 23 |
+
|
| 24 |
+
> A star and a gun is all you need
|
| 25 |
+
|
| 26 |
+
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.
|
| 27 |
+
<br><br>
|
| 28 |
+
[Dynamic FP8](https://huggingface.co/aetherwiing/MN-12B-Starcannon-v2-fp8-dynamic) <br>
|
| 29 |
+
[Static GGUF (by Mradermacher)](https://huggingface.co/mradermacher/MN-12B-Starcannon-v2-GGUF) <br>
|
| 30 |
+
[EXL2 (by kingbri of RoyalLab)](https://huggingface.co/royallab/MN-12B-Starcannon-v2-exl2)
|
| 31 |
+
## Merge Details
|
| 32 |
+
### Merge Method
|
| 33 |
+
|
| 34 |
+
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.
|
| 35 |
+
|
| 36 |
+
### Merge fodder
|
| 37 |
+
|
| 38 |
+
The following models were included in the merge:
|
| 39 |
+
* [nothingiisreal/MN-12B-Celeste-V1.9](https://huggingface.co/nothingiisreal/MN-12B-Celeste-V1.9)
|
| 40 |
+
* [intervitens/mini-magnum-12b-v1.1](https://huggingface.co/intervitens/mini-magnum-12b-v1.1)
|
| 41 |
+
|
| 42 |
+
### Configuration
|
| 43 |
+
|
| 44 |
+
The following YAML configuration was used to produce this model:
|
| 45 |
+
|
| 46 |
+
```yaml
|
| 47 |
+
models:
|
| 48 |
+
- model: intervitens/mini-magnum-12b-v1.1
|
| 49 |
+
parameters:
|
| 50 |
+
density: 0.3
|
| 51 |
+
weight: 0.5
|
| 52 |
+
- model: nothingiisreal/MN-12B-Celeste-V1.9
|
| 53 |
+
parameters:
|
| 54 |
+
density: 0.7
|
| 55 |
+
weight: 0.5
|
| 56 |
+
|
| 57 |
+
merge_method: ties
|
| 58 |
+
base_model: nothingiisreal/MN-12B-Celeste-V1.9
|
| 59 |
+
parameters:
|
| 60 |
+
normalize: true
|
| 61 |
+
int8_mask: true
|
| 62 |
+
dtype: bfloat16
|
| 63 |
+
|
| 64 |
+
```
|