base_model: | |
- mergekit-community/mergekit-model_stock-zjszwdf | |
- dreamgen/lucid-v1-nemo | |
- ReadyArt/Omega-Darker_The-Final-Directive-12B | |
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 | |
### Merge Method | |
This model was merged using the [DELLA](https://arxiv.org/abs/2406.11617) merge method using [mergekit-community/mergekit-model_stock-zjszwdf](https://huggingface.co/mergekit-community/mergekit-model_stock-zjszwdf) as a base. | |
### Models Merged | |
The following models were included in the merge: | |
* [dreamgen/lucid-v1-nemo](https://huggingface.co/dreamgen/lucid-v1-nemo) | |
* [ReadyArt/Omega-Darker_The-Final-Directive-12B](https://huggingface.co/ReadyArt/Omega-Darker_The-Final-Directive-12B) | |
### Configuration | |
The following YAML configuration was used to produce this model: | |
```yaml | |
base_model: mergekit-community/mergekit-model_stock-zjszwdf | |
merge_method: della | |
models: | |
- model: ReadyArt/Omega-Darker_The-Final-Directive-12B | |
parameters: | |
weight: 0.5 | |
- model: dreamgen/lucid-v1-nemo | |
parameters: | |
weight: 0.5 | |
parameters: | |
density: 0.67 | |
normalize: true | |
epsilon: 0.1 | |
lambda: 1 | |
tokenizer_source: union | |
chat_template: "chatml" | |
dtype: bfloat16 | |
``` | |