Qwen3-4B-Instruct-Thinking-SLERP / mergekit_config.yml
thiflaf's picture
Upload folder using huggingface_hub
887d3c1 verified
raw
history blame contribute delete
352 Bytes
slices:
- sources:
- model: Qwen/Qwen3-4B-Instruct-2507
layer_range: [0, 32]
- model: Qwen/Qwen3-4B-Thinking-2507
layer_range: [0, 32]
merge_method: slerp
base_model: Qwen/Qwen3-4B-Instruct-2507
parameters:
t:
- filter: self_attn
value: 0.5
- filter: mlp
value: 0.5
- value: 0.5
dtype: bfloat16