README.md

---
base_model: []
library_name: transformers
tags:
- mergekit
- merge

---
# Smolphin_llama3

This is a merge of pre-trained language models abacusai_Llama-3-Smaug-8B and cognitivecomputations_dolphin-2.9-llama3-8b created using [mergekit](https://github.com/cg123/mergekit).

<figure>

![Smolphin](Smolphin.PNG)  

</figure>



## Merge Details
### Merge Method

This model was merged using the SLERP merge method.

### Models Merged

The following models were included in the merge:
* abacusai_Llama-3-Smaug-8B
* cognitivecomputations_dolphin-2.9-llama3-8b

### Configuration

The following YAML configuration was used to produce this model:

```yaml
slices:
  - sources:
      - model: E:\cognitivecomputations_dolphin-2.9-llama3-8b
        layer_range: [0, 32]
      - model: E:\abacusai_Llama-3-Smaug-8B
        layer_range: [0, 32]
merge_method: slerp
base_model: E:\cognitivecomputations_dolphin-2.9-llama3-8b
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16

```