---
base_model:
- Sao10K/MN-12B-Lyra-v1
- Nohobby/YetAnotherMerge-v0.1
- Undi95/Lumimaid-Magnum-12B
library_name: transformers
tags:
- mergekit
- merge

---
# merge

This one turned out really good imo. Works fine with the basic min-p settings, but I recommend using [this](https://huggingface.co/Nohobby/YetAnotherMerge-v0.3/resolve/main/Yamyam.json?download=true) preset I made.

[iMatrix GGUF](https://huggingface.co/mradermacher/YetAnotherMerge-v0.3-i1-GGUF)
[Static GGUF](https://huggingface.co/mradermacher/YetAnotherMerge-v0.3-GGUF)

## Merge Details
### Merge Method

This model was merged using the della merge method using [Undi95/Lumimaid-Magnum-12B](https://huggingface.co/Undi95/Lumimaid-Magnum-12B) as a base.

### Models Merged

The following models were included in the merge:
* [Sao10K/MN-12B-Lyra-v1](https://huggingface.co/Sao10K/MN-12B-Lyra-v1)
* [Nohobby/YetAnotherMerge-v0.1](https://huggingface.co/Nohobby/YetAnotherMerge-v0.1)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
base_model: Undi95/Lumimaid-Magnum-12B
parameters:
  int8_mask: true
  rescale: true
  normalize: false
merge_method: della
dtype: bfloat16
models:
  - model: Sao10K/MN-12B-Lyra-v1
    parameters:
      density: [0.4, 0.5, 0.6, 0.4, 0.6, 0.5, 0.4]
      epsilon: [0.15, 0.15, 0.25, 0.15, 0.15]
      lambda: 0.85
      weight: [0.6, 0.5, 0.4, 0.6, 0.4, 0.5, 0.6]
  - model: Nohobby/YetAnotherMerge-v0.1
    parameters:
      density: [0.45, 0.55, 0.45, 0.55, 0.45]
      epsilon: [0.1, 0.1, 0.25, 0.1, 0.1]
      lambda: 0.85
      weight: [0.55, 0.45, 0.55, 0.45, 0.55]
```