Downloads · 30 days
35
10% of all-time downloads
DoppelReflEx/MN-12B-WolFrame
MN-12B-WolFrame is a text generation model from DoppelReflEx. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as cc-by-nc-4.0.
Previous name was WhiteSnake-V2, but the eval scores is not good, so I decide to rename it. Very good in creative writing and RP, ERP. Not good in Math.
Downloads · 30 days
35
10% of all-time downloads
All-time downloads
335
Public
Parameters
12.2B
49 GB on disk
Likes
6
Public
Click a slice to open those files.
.safetensors24.5 GB · 100%
From the Hugging Face model README
Previous name was WhiteSnake-V2, but the eval scores is not good, so I decide to rename it. Very good in creative writing and RP, ERP. Not good in Math.
It's main goal is to break the origin WhiteSnake in eval and real usecase, but nothing too good, just decent.
GGUF, thank mradermacher a lots: https://huggingface.co/mradermacher/MN-12B-Mimicore-WhiteSnake-v2-Experiment-4-GGUF
My own Q6_K: https://huggingface.co/DoppelReflEx/MN-12B-WolFrame-Q6_K-GGUF
<details> <summary>Merge Details</summary> <p> ### Models MergedThe following models were included in the merge:
The following YAML configuration was used to produce this model:
models:
- model: cgato/Nemo-12b-Humanize-KTO-Experimental-Latest
parameters:
density: 0.9
weight: 1
- model: DoppelReflEx/MN-12B-Mimicore-GreenSnake
parameters:
density: 0.6
weight: 0.8
- model: crestf411/MN-Slush
parameters:
density: 0.7
weight: 0.5
merge_method: dare_ties
base_model: IntervitensInc/Mistral-Nemo-Base-2407-chatml
tokenizer_source: base
</p>
</details>