README.md

---
base_model:
- Epiculous/Violet_Twilight-v0.2
- Nitral-AI/Captain_BMO-12B
library_name: transformers
tags:
- mergekit
- merge

---

![image/png](https://cdn-uploads.huggingface.co/production/uploads/642265bc01c62c1e4102dc36/V4OFnx7IBvXhYphdkUr5F.png)

![image/png](https://cdn-uploads.huggingface.co/production/uploads/642265bc01c62c1e4102dc36/VPFYDUBubiO3raJDFK_ii.png)

# Instruct/Context import + Textgen preset combined both available: [Here](https://huggingface.co/Nitral-AI/Captain_Violet-V0.420-12B/tree/main/ST) 

## Quants: [4bpw-exl2](https://huggingface.co/Nitral-AI/Captain-Eris_Violet-V0.420-12B-4bpw-exl2) Thanks to Mradermaacher for: [GGUF](https://huggingface.co/mradermacher/Captain-Eris_Violet-V0.420-12B-GGUF)

## Original Models used in the merge:
[Epiculous/Violet_Twilight-v0.2](https://huggingface.co/Epiculous/Violet_Twilight-v0.2)
[Nitral-AI/Captain_BMO-12B](https://huggingface.co/Nitral-AI/Captain_BMO-12B)


### The following YAML configuration was used to produce this model:

```yaml
slices:
  - sources:
      - model: Nitral-AI/Captain_BMO-12B
        layer_range: [0, 40]
      - model: Epiculous/Violet_Twilight-v0.2
        layer_range: [0, 40]
merge_method: slerp
base_model: Nitral-AI/Captain_BMO-12B
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: 0.420
dtype: bfloat16
```