---
base_model:
- tensorplex-labs/pretraining-sn9-7B-5
- skai24/sn9-7
- tensorplex-labs/pretraining-sn9-7B-1
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 [TIES](https://arxiv.org/abs/2306.01708) merge method using [tensorplex-labs/pretraining-sn9-7B-1](https://huggingface.co/tensorplex-labs/pretraining-sn9-7B-1) as a base.

### Models Merged

The following models were included in the merge:
* [tensorplex-labs/pretraining-sn9-7B-5](https://huggingface.co/tensorplex-labs/pretraining-sn9-7B-5)
* [skai24/sn9-7](https://huggingface.co/skai24/sn9-7)

### Configuration

The following YAML configuration was used to produce this model:

```yaml

models:
  - model: tensorplex-labs/pretraining-sn9-7B-1
    # no parameters necessary for base model
  - model: tensorplex-labs/pretraining-sn9-7B-5
    parameters:
      density: 0.5
      weight: 0.7
  - model: skai24/sn9-7
    parameters:
      density: 0.5
      weight: 0.3
merge_method: ties
base_model: tensorplex-labs/pretraining-sn9-7B-1
parameters:
  normalize: true
dtype: bfloat16

```