---
base_model:
- WWTCyberLab/gemma-4-E2B-it-abliterated
- google/gemma-4-E2B-it
library_name: transformers
tags:
- mergekit
- merge
- gemma
- gemma4
- gemma4_E2B

---
# 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](https://arxiv.org/abs/2203.05482) merge method using [google/gemma-4-E2B-it](https://huggingface.co/google/gemma-4-E2B-it) as a base.

### Models Merged

The following models were included in the merge:
* [WWTCyberLab/gemma-4-E2B-it-abliterated](https://huggingface.co/WWTCyberLab/gemma-4-E2B-it-abliterated)

### Configuration

The following YAML configuration was used to produce this model:

```yaml

models:
  - model: google/gemma-4-E2B-it
    parameters:
      density: 0.5
      weight: 0.32

  - model: WWTCyberLab/gemma-4-E2B-it-abliterated
    parameters:
      density: 0.5
      weight: 0.68

merge_method: linear
base_model: google/gemma-4-E2B-it
parameters:
  normalize: true
dtype: bfloat16
tokenizer_source: base

```
EN

The files used for merging are located at the following address: https://huggingface.co/zelk12/Mergekit_Gemma-4-E2B

___
___

RU

Файлы, которые использовались для объединения находятся по следующему адресу: https://huggingface.co/zelk12/Mergekit_Gemma-4-E2B