---
base_model_relation: quantized
library_name: transformers
tags:
- mergekit
- merge
base_model:
- TareksTesting/Legion-V2-LLaMa-70B
---
# 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 [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using [TareksLab/L2-MERGE1](https://huggingface.co/TareksLab/L2-MERGE1) as a base.

### Models Merged

The following models were included in the merge:
* [TareksLab/L2-MERGE2a](https://huggingface.co/TareksLab/L2-MERGE2a)
* [TareksLab/L2-MERGE3](https://huggingface.co/TareksLab/L2-MERGE3)
* [TareksLab/L-BASE-V1](https://huggingface.co/TareksLab/L-BASE-V1)
* [TareksLab/L2-MERGE4](https://huggingface.co/TareksLab/L2-MERGE4)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: TareksLab/L2-MERGE2a
    parameters:
      weight: 0.20
      density: 0.5
  - model: TareksLab/L-BASE-V1
    parameters:
      weight: 0.20
      density: 0.5
  - model: TareksLab/L2-MERGE4
    parameters:
      weight: 0.20
      density: 0.5
  - model: TareksLab/L2-MERGE3
    parameters:
      weight: 0.20
      density: 0.5
  - model: TareksLab/L2-MERGE1
    parameters:
      weight: 0.20
      density: 0.5
merge_method: dare_ties
base_model: TareksLab/L2-MERGE1
parameters:
  normalize: false
out_dtype: bfloat16
chat_template: llama3
tokenizer:
 source: base
```