base_model: [] | |
library_name: transformers | |
tags: | |
- mergekit | |
- merge | |
# output-model-directory | |
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 SLERP merge method. | |
### Models Merged | |
The following models were included in the merge: | |
* ./models/Moistral-11B-v2 | |
* ./models/RoleBeagle-11B | |
### Configuration | |
The following YAML configuration was used to produce this model: | |
```yaml | |
models: | |
- model: ./models/Moistral-11B-v2 | |
- model: ./models/RoleBeagle-11B | |
merge_method: slerp | |
base_model: ./models/Moistral-11B-v2 | |
parameters: | |
t: | |
- filter: self_attn | |
value: [0, 0.7, 0.5, 0.8, 1] # Increased influence of Moistral model | |
- filter: mlp | |
value: [1, 0.3, 0.5, 0.2, 0] # Decreased influence of RoleBeagle model | |
- value: 0.7 # Increased fallback value for rest of tensors | |
dtype: float16 | |
``` | |