---
base_model:
- TareksLab/Wordforger-V1b-LLaMa-70B
- unsloth/Llama-3.3-70B-Instruct
- Nohobby/AbominationSnowPig
- TareksLab/RolePlayer-V6-LLaMa-70B
library_name: transformers
tags:
- mergekit
- merge

---
# merge

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

## Merge Details
### Merge Method

This model was merged using the [Model Breadcrumbs](https://arxiv.org/abs/2312.06795) merge method using [unsloth/Llama-3.3-70B-Instruct](https://huggingface.co/unsloth/Llama-3.3-70B-Instruct) as a base.

### Models Merged

The following models were included in the merge:
* [TareksLab/Wordforger-V1b-LLaMa-70B](https://huggingface.co/TareksLab/Wordforger-V1b-LLaMa-70B)
* [Nohobby/AbominationSnowPig](https://huggingface.co/Nohobby/AbominationSnowPig)
* [TareksLab/RolePlayer-V6-LLaMa-70B](https://huggingface.co/TareksLab/RolePlayer-V6-LLaMa-70B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: unsloth/Llama-3.3-70B-Instruct
  - model: Nohobby/AbominationSnowPig
    parameters:
        density: 0.4
        gamma: 0.05
        weight: 0.4
  - model: TareksLab/Wordforger-V1b-LLaMa-70B
    parameters:
        density: 0.4
        gamma: 0.07
        weight: 0.4
  - model: TareksLab/RolePlayer-V6-LLaMa-70B
    parameters:
        density: 0.5
        gamma: 0.05
        weight: 0.2
base_model: unsloth/Llama-3.3-70B-Instruct
merge_method: breadcrumbs
parameters:
  int8_mask: true
  rescale: true
  normalize: false
dtype: bfloat16
tokenizer_source: base
```