|
--- |
|
base_model: |
|
- anthracite-org/magnum-v3-9b-chatml |
|
- grimjim/Kitsunebi-v1-Gemma2-8k-9B |
|
library_name: transformers |
|
pipeline_tag: text-generation |
|
tags: |
|
- mergekit |
|
- merge |
|
license: gemma |
|
--- |
|
# Magot-v3-Gemma2-8k-9B |
|
|
|
This repo contains a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). |
|
|
|
This series of models is an attempt to combine the strengths of Instruct models with the creativity of Magnum models while balancing text generation on the shorter side compared to undiluted Magnum. |
|
|
|
Tested at temp=1, minP=0.01. |
|
|
|
This attempt seems more solid than earlier versions in the series. Coherence is moderately high. Unfortunately, some recency bias remains. |
|
|
|
## Merge Details |
|
### Merge Method |
|
|
|
This model was merged using the SLERP merge method. |
|
|
|
### Models Merged |
|
|
|
The following models were included in the merge: |
|
* [anthracite-org/magnum-v3-9b-chatml](https://huggingface.co/anthracite-org/magnum-v3-9b-chatml) |
|
* [grimjim/Kitsunebi-v1-Gemma2-8k-9B](https://huggingface.co/grimjim/Kitsunebi-v1-Gemma2-8k-9B) |
|
|
|
### Configuration |
|
|
|
The following YAML configuration was used to produce this model: |
|
|
|
```yaml |
|
models: |
|
- model: grimjim/Kitsunebi-v1-Gemma2-8k-9B |
|
- model: anthracite-org/magnum-v3-9b-chatml |
|
merge_method: slerp |
|
base_model: grimjim/Kitsunebi-v1-Gemma2-8k-9B |
|
parameters: |
|
t: |
|
- value: 0.2 |
|
dtype: bfloat16 |
|
|
|
``` |
|
|
