Request
#1003
by
Enderchef
- opened
Does somebody know how to merge these properly this and apps/sites that will merge it for me?
slices:
- sources:
- model: radna/S1.1-Deepseek-R1-QwQ-32B-Preview
layer_range: [0, 32] - model: Ba2han/QwQenSeek-coder
layer_range: [0, 32]
- model: radna/S1.1-Deepseek-R1-QwQ-32B-Preview
merge_method: slerp
base_model:
model: Qwen/Qwen2.5-32B
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
dtype: float16
Is the syntax correct?
Just try it and it will complain if the syntax is wrong. I'm not your syntax verifyer and this is for model requests and not to help you verify the syntax of your config file. Maybe if you put it into a yaml code block you would at least see the syntax highlighting. There is an entire mergekit community on HuggingFace so maybe ask there if you have issues creating a merge but looks good.