---
base_model:
- google/gemma-4-12B-it
- tepirale/gemma-4-12B-coder-fable5-composer2.5-v1-safetensors-yuxinlu1
- tepirale/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-safetensors-yuxinlu1
library_name: transformers
tags:
- mergekit
- merge

---
# merged-gemma4-12b

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 [Task Arithmetic](https://arxiv.org/abs/2212.04089) merge method using [google/gemma-4-12B-it](https://huggingface.co/google/gemma-4-12B-it) as a base.

### Models Merged

The following models were included in the merge:
* [tepirale/gemma-4-12B-coder-fable5-composer2.5-v1-safetensors-yuxinlu1](https://huggingface.co/tepirale/gemma-4-12B-coder-fable5-composer2.5-v1-safetensors-yuxinlu1)
* [tepirale/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-safetensors-yuxinlu1](https://huggingface.co/tepirale/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-safetensors-yuxinlu1)

### Configuration

The following YAML configuration was used to produce this model:

```yaml

merge_method: task_arithmetic
base_model: google/gemma-4-12B-it
dtype: bfloat16
parameters:
  normalize: true
models:
  - model: google/gemma-4-12B-it
    parameters:
      weight: 1.0 # Base limpia que mantiene la estructura gramatical
  - model: tepirale/gemma-4-12B-coder-fable5-composer2.5-v1-safetensors-yuxinlu1
    parameters:
      weight: 0.35 # Inyecta la habilidad de código puro
  - model: tepirale/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-safetensors-yuxinlu1
    parameters:
      weight: 0.35 # Inyecta la lógica y uso de herramientas de agente

```