---
base_model: []
library_name: transformers
tags:
- mergekit
- merge

---
# WeirdCompound-v1.1-24b

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

## Merge Details
### Notes

This is a multi-stage merge. There's little method to my madness and I just stopped when I arrived at something that I liked.

Starting point was DepravedCartographer-v1.0-24b with slight changes.

Mistral released 3.2 2506, so I wanted to see how these slerp merges would turn out with it in the tree, even if none of the other models is a strict descendant of Mistral 3.2. Seems to be coherent enough, so I'm uploading this. No clue how many of the 3.2 improvements survived the process though.

### Changelog

v1.1
* /intermediate/model/B: replaced anthracite-core/Mistral-Small-3.1-24B-Instruct-2503-HF with anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-ChatML

### Merge Method

This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [TheDrummer/Cydonia-24B-v3](https://huggingface.co/TheDrummer/Cydonia-24B-v3) as a base.

This model was merged using the [SLERP](https://en.wikipedia.org/wiki/Slerp) merge method.

This model was merged using the NuSLERP merge method using /intermediate/model/B as a base.

### Models Merged

The following models were included in the merge:
* [Delta-Vector/Austral-24B-Winton](https://huggingface.co/Delta-Vector/Austral-24B-Winton)
* [Doctor-Shotgun/MS3.1-24B-Magnum-Diamond](https://huggingface.co/Doctor-Shotgun/MS3.1-24B-Magnum-Diamond)
* [aixonlab/Eurydice-24b-v3.5](https://huggingface.co/aixonlab/Eurydice-24b-v3.5)
* [PocketDoc/Dans-PersonalityEngine-V1.3.0-24b](https://huggingface.co/PocketDoc/Dans-PersonalityEngine-V1.3.0-24b)
* [anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-ChatML](https://huggingface.co/anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-ChatML)
* /intermediate/model/A
* /intermediate/model/B
* /intermediate/model/C

### Configuration

The following YAML configuration was used to produce this model:

```yaml
base_model: TheDrummer/Cydonia-24B-v3 # Cydonia v3
merge_method: model_stock
dtype: bfloat16
models:
  - model: aixonlab/Eurydice-24b-v3.5 # storytelling / RP
  - model: TheDrummer/Cydonia-24B-v3 # sprinkle in some extra Cydonia v3
  - model: PocketDoc/Dans-PersonalityEngine-V1.3.0-24b # Prompt Adherence
  - model: Delta-Vector/Austral-24B-Winton  # Adventure
  - model: Doctor-Shotgun/MS3.1-24B-Magnum-Diamond # claude opus
```
→ `/intermediate/model/A` →

```yaml
merge_method: slerp
dtype: bfloat16
base_model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-ChatML
models:
  - model: /intermediate/model/A
parameters:
  t: 0.4

```

→ `/intermediate/model/B` →

```yaml
merge_method: nuslerp
dtype: bfloat16
base_model: /intermediate/model/B
models:
  - model: PocketDoc/Dans-PersonalityEngine-V1.3.0-24b
    parameters:
      weight: 0.6
  - model: aixonlab/Eurydice-24b-v3.5
    parameters:
      weight: 0.4

```

→ `/intermediate/model/C` →

```yaml
merge_method: slerp
dtype: bfloat16
base_model: /intermediate/model/B
models:
  - model: /intermediate/model/C
parameters:
  t: 0.5

```

→ WeirdCompound-v1.1-24b