license: apache-2.0 | |
tags: | |
- merge | |
- mergekit | |
- lazymergekit | |
- Qwen/Qwen3-4B | |
- netcat420/qwen3-MFANN-4b | |
# qwen3-4b-MFANN-slerp | |
qwen3-4b-MFANN-slerp is a merge of the following models using [mergekit](https://github.com/cg123/mergekit): | |
* [Qwen/Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B) | |
* [netcat420/qwen3-MFANN-4b](https://huggingface.co/netcat420/qwen3-MFANN-4b) | |
## 🧩 Configuration | |
```yaml | |
slices: | |
- sources: | |
- model: Qwen/Qwen3-4B | |
layer_range: [0, 36] | |
- model: netcat420/qwen3-MFANN-4b | |
layer_range: [0, 36] | |
merge_method: slerp | |
base_model: Qwen/Qwen3-4B | |
parameters: | |
t: | |
- filter: self_attn | |
value: [0, 0.5, 0.3, 0.7, 1] | |
- filter: mlp | |
value: [1, 0.5, 0.7, 0.3, 0] | |
- value: 0.5 # fallback for rest of tensors | |
dtype: float16 | |
``` |