---
base_model:
- TareksLab/Fifth-Dimension-V1-LLaMa-70B
- TareksLab/Third-Dimension-V1-LLaMa-70B
- TareksLab/Second-Dimension-V1-LLaMa-70B
- TareksLab/Zero-Dimension-F-LLaMa-70B
- TareksLab/Sixth-Dimension-V1-LLaMa-70B
- TareksLab/First-Dimension-V1-LLaMa-70B
library_name: transformers
tags:
- mergekit
- merge

---
# MERGE6

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/Second-Dimension-V1-LLaMa-70B](https://huggingface.co/TareksLab/Second-Dimension-V1-LLaMa-70B) as a base.

### Models Merged

The following models were included in the merge:
* [TareksLab/Fifth-Dimension-V1-LLaMa-70B](https://huggingface.co/TareksLab/Fifth-Dimension-V1-LLaMa-70B)
* [TareksLab/Third-Dimension-V1-LLaMa-70B](https://huggingface.co/TareksLab/Third-Dimension-V1-LLaMa-70B)
* [TareksLab/Zero-Dimension-F-LLaMa-70B](https://huggingface.co/TareksLab/Zero-Dimension-F-LLaMa-70B)
* [TareksLab/Sixth-Dimension-V1-LLaMa-70B](https://huggingface.co/TareksLab/Sixth-Dimension-V1-LLaMa-70B)
* [TareksLab/First-Dimension-V1-LLaMa-70B](https://huggingface.co/TareksLab/First-Dimension-V1-LLaMa-70B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: TareksLab/Sixth-Dimension-V1-LLaMa-70B
    parameters:
      weight: [0.1, 0.1, 0.1, 0.2, 0.5]
  - model: TareksLab/Fifth-Dimension-V1-LLaMa-70B
    parameters:
      weight: [0.1, 0.1, 0.2, 0.4, 0.2]
  - model: TareksLab/Zero-Dimension-F-LLaMa-70B
    parameters:
      weight: [0.1, 0.2, 0.4, 0.2, 0.1]
  - model: TareksLab/Third-Dimension-V1-LLaMa-70B
    parameters:
      weight: [0.2, 0.4, 0.2, 0.1, 0.1]
  - model: TareksLab/First-Dimension-V1-LLaMa-70B
    parameters:
      weight: [0.5, 0.2, 0.1, 0.1, 0.1]
merge_method:  multislerp
base_model: TareksLab/Second-Dimension-V1-LLaMa-70B
parameters:
  normalize: false
dtype: float32
out_dtype: bfloat16
chat_template: llama3
tokenizer:
 source: TareksLab/Zero-Dimension-F-LLaMa-70B
 pad_to_multiple_of: 8

```