README.md

---
base_model:
- Local-Novel-LLM-project/kagemusya-7B-v1
- DataPilot/ArrowPro-7B-RobinHood
library_name: transformers
tags:
- mergekit
- merge

---

 　たぶん現存する小説型モデルの中だとこれが最強。RobinHoodはやけに指示性能がいい。そして、kagemusyaは指示性能や会話性能は低いけど小説は地の文や会話のある、小説を書ける。この二つをマージすることでちょうどいい具合の最強の小説モデルができたｂ　ロールプレイもやらせると小説のように人間味がある会話ができる。

# 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 [TIES](https://arxiv.org/abs/2306.01708) merge method using [Local-Novel-LLM-project/kagemusya-7B-v1](https://huggingface.co/Local-Novel-LLM-project/kagemusya-7B-v1) as a base.

### Models Merged

The following models were included in the merge:
* [DataPilot/ArrowPro-7B-RobinHood](https://huggingface.co/DataPilot/ArrowPro-7B-RobinHood)

### Configuration

The following YAML configuration was used to produce this model:

```yaml

models:
  - model: Local-Novel-LLM-project/kagemusya-7B-v1
    parameters:
      weight: 1
  - model: DataPilot/ArrowPro-7B-RobinHood
    parameters:
      weight: 0.7
merge_method: ties
base_model: Local-Novel-LLM-project/kagemusya-7B-v1
parameters:
  normalize: false
dtype: bfloat16

```