---
base_model:
- Undi95/Meta-Llama-3.1-8B-Claude
library_name: transformers
tags:
- mergekit
- merge

---
# stablerp

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-3.1-8B-Claude](https://huggingface.co/Undi95/Meta-Llama-3.1-8B-Claude) as a base.

### Models Merged

The following models were included in the merge:
* merge/stablerp.c
* merge/stablerp.a
* merge/stablerp.b

### Configuration

The following YAML configuration was used to produce this model:

```yaml
base_model: Undi95/Meta-Llama-3.1-8B-Claude
dtype: float32
merge_method: dare_linear
out_dtype: bfloat16
parameters:
  int8_mask: 1.0
  normalize: 0.0
slices:
- sources:
  - layer_range: [0, 32]
    model: merge/stablerp.b
    parameters:
      weight: [1.0, 0.2]
  - layer_range: [0, 32]
    model: merge/stablerp.a
    parameters:
      weight: [0.1, 0.5]
  - layer_range: [0, 32]
    model: merge/stablerp.c
    parameters:
      weight: [0.1, 0.5]
  - layer_range: [0, 32]
    model: Undi95/Meta-Llama-3.1-8B-Claude
tokenizer_source: base
```