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

---
# L3.1-Instruct-Guru

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](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using G:/7B/Meta-Llama-3.1-8B-Instruct as a base.

### Models Merged

The following models were included in the merge:
* G:/7B/Llama-3.1-8B-Claude
* G:/7B/Llama-3.1-Storm-8B
* G:/7B/Llama-3.1-SuperNova-Lite

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: G:/7B/Llama-3.1-8B-Claude
    parameters:
      weight: [1,1,.75,.5,.25,.25,.05,.01]
  - model: G:/7B/Llama-3.1-Storm-8B
    parameters:
      weight: [0,0,.25,.35,.4,.25,.30,.04]
  - model: G:/7B/Llama-3.1-SuperNova-Lite
    parameters:
      weight: [0,0,0,.15,.35,.5,.65,.95]
merge_method: dare_ties
base_model: G:/7B/Meta-Llama-3.1-8B-Instruct
dtype: bfloat16

```