Llama-3-Luminurse-v0.2-OAS-8B / mergekit_config.yml
grimjim's picture
Initial release
4584087
raw
history blame
397 Bytes
base_model: NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS
slices:
- sources:
- model: NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS
layer_range: [0,32]
- model: grimjim/llama-3-aaditya-OpenBioLLM-8B
layer_range: [0,32]
parameters:
weight: 0.2
- model: cgato/L3-TheSpice-8b-v0.8.3
layer_range: [0,32]
parameters:
weight: 0.04
merge_method: task_arithmetic
dtype: bfloat16