Llama-3-Oasis-v1-OAS-8B / mergekit_config.yml
grimjim's picture
Initial release
d8ea2ff
raw
history blame
403 Bytes
base_model: mlabonne/NeuralDaredevil-8B-abliterated
dtype: bfloat16
merge_method: task_arithmetic
slices:
- sources:
- layer_range: [0, 32]
model: mlabonne/NeuralDaredevil-8B-abliterated
- layer_range: [0, 32]
model: NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS
parameters:
weight: 0.3
- layer_range: [0, 32]
model: Hastagaras/Halu-OAS-8B-Llama3
parameters:
weight: 0.3