README.md

---
base_model:
- darkc0de/XortronCriminalComputingConfig
- TheDrummer/Cydonia-24B-v3
- Sorawiz/MistralCreative-24B-Chat
library_name: transformers
tags:
- mergekit
- merge

---

~ The power of Three

![image.png](https://huggingface.co/Entropicengine/Trifecta-Max-24b/resolve/main/generation-51e6b898-485d-43a0-9d6c-69fb24ad1c41%20(1).png)

# Trifecta-Max-24b

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

# Recommended ST preset for RP : 
- [Sphiratrioth](https://huggingface.co/sphiratrioth666/SillyTavern-Presets-Sphiratrioth)

# ☕ Support My Work  
If you like my work, consider [buying me a coffee](https://ko-fi.com/entropicengine) to support future merges, GPU time, and experiments.
  
## Merge Details
### Merge Method

This model was merged using the [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using [darkc0de/XortronCriminalComputingConfig](https://huggingface.co/darkc0de/XortronCriminalComputingConfig) as a base.

### Models Merged

The following models were included in the merge:
* [TheDrummer/Cydonia-24B-v3](https://huggingface.co/TheDrummer/Cydonia-24B-v3)
* [Sorawiz/MistralCreative-24B-Chat](https://huggingface.co/Sorawiz/MistralCreative-24B-Chat)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
base_model: darkc0de/XortronCriminalComputingConfig
chat_template: auto
merge_method: dare_ties
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 40]
        model: darkc0de/XortronCriminalComputingConfig
        parameters:
          weight: 0.4
      - layer_range: [0, 40]
        model: Sorawiz/MistralCreative-24B-Chat
        parameters:
          weight: 0.3
      - layer_range: [0, 40]
        model: TheDrummer/Cydonia-24B-v3
        parameters:
          weight: 0.3
out_dtype: bfloat16
parameters:
  density: 1.0
tokenizer: {}
```