40 lines
790 B
Markdown
40 lines
790 B
Markdown
---
|
|
base_model: []
|
|
library_name: transformers
|
|
tags:
|
|
- mergekit
|
|
- merge
|
|
|
|
---
|
|
# Violet-Lyra-Gutenberg-v2-12b
|
|
|
|
Update:
|
|
Actually I do not really like its prose. It is more stable, though. Interestingly it scored amazing on UGI leaderboard. I do think this model is really smart though.
|
|
|
|
# Prompt format:
|
|
ChatML
|
|
|
|
```yaml
|
|
models:
|
|
- model: redrix/AngelSlayer-12B-Unslop-Mell-RPMax-DARKNESS
|
|
parameters:
|
|
weight: 0.3
|
|
- model: Nitral-AI/Captain_Eris_Noctis-12B-v0.420
|
|
parameters:
|
|
weight: 0.3
|
|
- model: ohyeah1/Violet-Lyra-Gutenberg
|
|
parameters:
|
|
weight: 0.6
|
|
base_model: mistralai/Mistral-Nemo-Base-2407
|
|
parameters:
|
|
density: 0.5
|
|
epsilon: 0.1
|
|
lambda: 1.0
|
|
normalize: false
|
|
rescale: true
|
|
merge_method: della_linear
|
|
tokenizer:
|
|
source: union
|
|
dtype: bfloat16
|
|
```
|