---
base_model:
- arcee-ai/Homunculus
- Nitral-Archive/Irix-12B-MS-Qwen3-Tokenizer
library_name: transformers
tags:
- mergekit
- merge

---
# I would like to train this out of personal curiosity, based on some qlora test runs for healing. However, due to financial constraints this will come at a later date.

### Models Merged

The following models were included in the merge:
* [arcee-ai/Homunculus](https://huggingface.co/arcee-ai/Homunculus)
* [Nitral-Archive/Irix-12B-MS-Qwen3-Tokenizer](https://huggingface.co/Nitral-Archive/Irix-12B-MS-Qwen3-Tokenizer)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
slices:
  - sources:
      - model: Nitral-Archive/Irix-12B-MS-Qwen3-Tokenizer
        layer_range: [0, 40]
      - model: arcee-ai/Homunculus
        layer_range: [0, 40]
merge_method: slerp
base_model: Nitral-Archive/Irix-12B-MS-Qwen3-Tokenizer
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: 0.69
dtype: bfloat16

```