README.md

---
base_model:
- TareksLab/Mithril-Prose-LLaMa-70B
- TareksLab/Mithril-Base-LLaMa-70B
- TareksLab/Mithril-ERP-LLaMa-70B
- TareksLab/Mithril-RP-LLaMa-70B
- TareksLab/Mithril-Thinker-Llama-70B
- TareksLab/Mithril-Creative-LLaMa-70B
library_name: transformers
tags:
- mergekit
- merge

---
# merged

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 [Multi-SLERP](https://goddard.blog/posts/multislerp-wow-what-a-cool-idea) merge method using [TareksLab/Mithril-Base-LLaMa-70B](https://huggingface.co/TareksLab/Mithril-Base-LLaMa-70B) as a base.

### Models Merged

The following models were included in the merge:
* [TareksLab/Mithril-Prose-LLaMa-70B](https://huggingface.co/TareksLab/Mithril-Prose-LLaMa-70B)
* [TareksLab/Mithril-ERP-LLaMa-70B](https://huggingface.co/TareksLab/Mithril-ERP-LLaMa-70B)
* [TareksLab/Mithril-RP-LLaMa-70B](https://huggingface.co/TareksLab/Mithril-RP-LLaMa-70B)
* [TareksLab/Mithril-Thinker-Llama-70B](https://huggingface.co/TareksLab/Mithril-Thinker-Llama-70B)
* [TareksLab/Mithril-Creative-LLaMa-70B](https://huggingface.co/TareksLab/Mithril-Creative-LLaMa-70B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: TareksLab/Mithril-Prose-LLaMa-70B
    parameters:
      weight: 0.2
  - model: TareksLab/Mithril-ERP-LLaMa-70B
    parameters:
      weight: 0.2
  - model: TareksLab/Mithril-RP-LLaMa-70B
    parameters:
      weight: 0.2
  - model: TareksLab/Mithril-Creative-LLaMa-70B
    parameters:
      weight: 0.2
  - model: TareksLab/Mithril-Thinker-Llama-70B
    parameters:
      weight: 0.2
base_model: TareksLab/Mithril-Base-LLaMa-70B
merge_method: multislerp
parameters:
  normalize_weights: false
  eps: 1e-9
chat_template: llama3
dtype: bfloat16
tokenizer:
  source: base
  pad_to_multiple_of: 8


```