---
base_model:
- UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
- princeton-nlp/gemma-2-9b-it-SimPO
library_name: transformers
tags:
- mergekit
- merge
license: gemma
pipeline_tag: text-generation
---
# Gemma2-Nephilim-v3-9B

This repo contains a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

Though none of the components of this merge were trained for roleplay nor intended for it, the model can be used effectively in that role.

Tested with temperature 1 and minP 0.01. This model leans toward being creative, so adjust temperature upward or downward as desired. The Instruct template used during testing can be found below:

- [context template](https://huggingface.co/debased-ai/SillyTavern-settings/blob/main/advanced_formatting/context_template/Gemma2%20Unleashed3.json)
- [instruct prompt](https://huggingface.co/debased-ai/SillyTavern-settings/blob/main/advanced_formatting/instruct_mode/Gemma2%20Unleashed3.json)

Afterword: In subsequent testing, I encountered an occasional lapse in tracking context for complex scenarios, which seems to originate in the SPPO model. This lapse is not present in [grimjim/Kitsunebi-v1-Gemma2-8k-9B](https://huggingface.co/grimjim/Kitsunebi-v1-Gemma2-8k-9B).

## Merge Details
### Merge Method

This model was merged using the SLERP merge method.

### Models Merged

The following models were included in the merge:
* [UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3](https://huggingface.co/UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3)
* [princeton-nlp/gemma-2-9b-it-SimPO](https://huggingface.co/princeton-nlp/gemma-2-9b-it-SimPO)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
slices:
- sources:
  - model: princeton-nlp/gemma-2-9b-it-SimPO
    layer_range:
    - 0
    - 42
  - model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
    layer_range:
    - 0
    - 42
merge_method: slerp
base_model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
parameters:
  t:
  - filter: self_attn
    value:
    - 0
    - 0.5
    - 0.3
    - 0.7
    - 1
  - filter: mlp
    value:
    - 1
    - 0.5
    - 0.7
    - 0.3
    - 0
  - value: 0.5
dtype: bfloat16

```