---
base_model:
- rubricreward/R3-Qwen3-4B-LoRA-4k
- rubricreward/R3-Qwen3-4B-14k
- Qwen/Qwen3-4B
- rubricreward/R3-Qwen3-4B-4k
library_name: transformers
tags:
- mergekit
- merge

---
# R3-Qwen3-4B_merged_ties

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 [Qwen/Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B) as a base.

### Models Merged

The following models were included in the merge:
* [rubricreward/R3-Qwen3-4B-LoRA-4k](https://huggingface.co/rubricreward/R3-Qwen3-4B-LoRA-4k)
* [rubricreward/R3-Qwen3-4B-14k](https://huggingface.co/rubricreward/R3-Qwen3-4B-14k)
* [rubricreward/R3-Qwen3-4B-4k](https://huggingface.co/rubricreward/R3-Qwen3-4B-4k)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: rubricreward/R3-Qwen3-4B-LoRA-4k
    parameters:
      weight: 0.4
  - model: rubricreward/R3-Qwen3-4B-4k
    parameters:
      weight: 0.3
  - model: rubricreward/R3-Qwen3-4B-14k
    parameters:
      weight: 0.3
merge_method: ties
base_model: Qwen/Qwen3-4B
lambda: 1.0
dtype: bfloat16

```