Neuralqwen3-0.5B-slerp / mergekit_config.yml
archit11's picture
Upload folder using huggingface_hub
22ab475 verified
slices:
- sources:
- model: KingNish/Qwen2.5-0.5b-Test-ft
layer_range: [0, 24]
- model: Replete-AI/Replete-LLM-V2.5-Qwen-0.5b
layer_range: [0, 24]
merge_method: slerp
base_model: KingNish/Qwen2.5-0.5b-Test-ft
parameters:
t:
- filter: "*"
value: [0.3, 0.4, 0.5, 0.6, 0.7]
dtype: bfloat16