|
--- |
|
base_model: [] |
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
|
|
--- |
|
# Instant-RP-Noodles-12B-v15 |
|
|
|
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_linear merge method using /home/james/Desktop/merge/mistral-nemo-bophades-12B as a base. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* /home/james/Desktop/merge/Lyra-Gutenberg-mistral-nemo-12B |
|
* /home/james/Desktop/merge/mistral-nemo-gutenberg-12B-v3 |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
models: |
|
- model: /home/james/Desktop/merge/Lyra-Gutenberg-mistral-nemo-12B |
|
parameters: |
|
weight: 0.23 |
|
density: 0.56 |
|
epsilon: 0.045 |
|
lambda: 1.01 |
|
- model: /home/james/Desktop/merge/mistral-nemo-gutenberg-12B-v3 |
|
parameters: |
|
weight: 0.33 |
|
density: 0.66 |
|
epsilon: 0.042 |
|
lambda: 1.03 |
|
- model: /home/james/Desktop/merge/mistral-nemo-bophades-12B |
|
parameters: |
|
weight: 0.44 |
|
density: 0.78 |
|
epsilon: 0.039 |
|
lambda: 1.05 |
|
merge_method: della_linear |
|
base_model: /home/james/Desktop/merge/mistral-nemo-bophades-12B |
|
dtype: bfloat16 |
|
tokenzer_source: union |
|
|
|
``` |
|
|
