---
base_model:
- google/gemma-3-4b-it-qat-int4-unquantized
- huihui-ai/gemma-3-4b-it-abliterated
- VIDraft/Gemma-3-R1984-4B
- neo4j/text-to-cypher-Gemma-3-4B-Instruct-2025.04.0
- google/medgemma-4b-it
- google/gemma-3-4b-it-qat-q4_0-unquantized
- ZySec-AI/gemma-3-4b-document-writer
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 [Karcher Mean](https://en.wikipedia.org/wiki/Karcher_mean) merge method using [google/gemma-3-4b-it-qat-q4_0-unquantized](https://huggingface.co/google/gemma-3-4b-it-qat-q4_0-unquantized) as a base.

### Models Merged

The following models were included in the merge:
* [google/gemma-3-4b-it-qat-int4-unquantized](https://huggingface.co/google/gemma-3-4b-it-qat-int4-unquantized)
* [huihui-ai/gemma-3-4b-it-abliterated](https://huggingface.co/huihui-ai/gemma-3-4b-it-abliterated)
* [VIDraft/Gemma-3-R1984-4B](https://huggingface.co/VIDraft/Gemma-3-R1984-4B)
* [neo4j/text-to-cypher-Gemma-3-4B-Instruct-2025.04.0](https://huggingface.co/neo4j/text-to-cypher-Gemma-3-4B-Instruct-2025.04.0)
* [google/medgemma-4b-it](https://huggingface.co/google/medgemma-4b-it)
* [ZySec-AI/gemma-3-4b-document-writer](https://huggingface.co/ZySec-AI/gemma-3-4b-document-writer)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: google/gemma-3-4b-it-qat-q4_0-unquantized
    layer_range: [0, 25]
  - model: google/gemma-3-4b-it-qat-int4-unquantized
    layer_range: [0, 25]
  - model: ZySec-AI/gemma-3-4b-document-writer
    layer_range: [0, 25]
  - model: neo4j/text-to-cypher-Gemma-3-4B-Instruct-2025.04.0
    layer_range: [0, 25]
  - model: huihui-ai/gemma-3-4b-it-abliterated
    layer_range: [0, 25]
  - model: VIDraft/Gemma-3-R1984-4B
    layer_range: [0, 25]
  - model: google/medgemma-4b-it
    layer_range: [0, 25]
merge_method: karcher
base_model: google/gemma-3-4b-it-qat-q4_0-unquantized
dtype: bfloat16
```