---
base_model:
- O1-OPEN/OpenO1-LLama-8B-v0.1
- huihui-ai/Llama-3.1-Tulu-3-8B-abliterated
- ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.2
- Undi95/Meta-Llama-3-8B-hf
- Sao10K/L3-8B-Stheno-v3.2
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 linear [DARE](https://arxiv.org/abs/2311.03099) merge method using [Undi95/Meta-Llama-3-8B-hf](https://huggingface.co/Undi95/Meta-Llama-3-8B-hf) as a base.

### Models Merged

The following models were included in the merge:
* [O1-OPEN/OpenO1-LLama-8B-v0.1](https://huggingface.co/O1-OPEN/OpenO1-LLama-8B-v0.1)
* [huihui-ai/Llama-3.1-Tulu-3-8B-abliterated](https://huggingface.co/huihui-ai/Llama-3.1-Tulu-3-8B-abliterated)
* [ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.2](https://huggingface.co/ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.2)
* [Sao10K/L3-8B-Stheno-v3.2](https://huggingface.co/Sao10K/L3-8B-Stheno-v3.2)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
merge_method: dare_linear  # Define the merging method (e.g., linear, dare_linear)
base_model: Undi95/Meta-Llama-3-8B-hf  # The base model for the merge
models:
  - model: Sao10K/L3-8B-Stheno-v3.2
    parameters:
      attention_heads: 0.6
      weight: 1.0  # Added missing weight parameter

  - model: ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.2
    parameters:
      feedforward: 0.4
      weight: 1.0  # Add weight for consistency

  - model: O1-OPEN/OpenO1-LLama-8B-v0.1
    parameters:
      all: 0.3
      weight: 1.0  # Add weight for consistency

  - model: huihui-ai/Llama-3.1-Tulu-3-8B-abliterated
    parameters:
      layer_norm: 0.2
      weight: 1.0  # Add weight for consistency

parameters:
  general: 0.6  # Default parameter for fallback
dtype: float16  # Data type for merging
tokenizer_source: union  # Tokenizer combining method
output_path: ./merged_model  # Output location for the merged model
```