---
base_model:
- BAAI/AREX-Turbo
- hotdogs/Agents-A1-4B-Fable-Preview-heretic
- CloudGoat/Mephisto-4B-0725
- br1-pist/Qwen3.5-4B-AgentCoder
- shuhulx/Qwopus3.5-4B-Coder-Fable5-v1
library_name: transformers
tags:
- mergekit
- merge

---
# Merged_AREX_4B

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 TIES](https://arxiv.org/abs/2311.03099) merge method using [BAAI/AREX-Turbo](https://huggingface.co/BAAI/AREX-Turbo) as a base.

### Models Merged

The following models were included in the merge:
* [hotdogs/Agents-A1-4B-Fable-Preview-heretic](https://huggingface.co/hotdogs/Agents-A1-4B-Fable-Preview-heretic)
* [CloudGoat/Mephisto-4B-0725](https://huggingface.co/CloudGoat/Mephisto-4B-0725)
* [br1-pist/Qwen3.5-4B-AgentCoder](https://huggingface.co/br1-pist/Qwen3.5-4B-AgentCoder)
* [shuhulx/Qwopus3.5-4B-Coder-Fable5-v1](https://huggingface.co/shuhulx/Qwopus3.5-4B-Coder-Fable5-v1)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
merge_method: dare_ties
base_model: BAAI/AREX-Turbo
models:
- model: BAAI/AREX-Turbo
- model: br1-pist/Qwen3.5-4B-AgentCoder
  parameters:
    weight: 0.3
    density: 0.6
- model: hotdogs/Agents-A1-4B-Fable-Preview-heretic
  parameters:
    weight: 0.24
    density: 0.55
- model: shuhulx/Qwopus3.5-4B-Coder-Fable5-v1
  parameters:
    weight: 0.18
    density: 0.5
- model: CloudGoat/Mephisto-4B-0725
  parameters:
    weight: 0.12
    density: 0.45
dtype: bfloat16

```