Bagel-Hermes-2-Pro-Llama3-8B / mergekit_config.yml
mrcuddle's picture
Upload folder using huggingface_hub
022c95d verified
raw
history blame contribute delete
387 Bytes
slices:
- sources:
- model: NousResearch/Hermes-2-Pro-Llama-3-8B
layer_range: [0, 32]
- model: jondurbin/bagel-8b-v1.0
layer_range: [0, 32]
merge_method: slerp
base_model: jondurbin/bagel-8b-v1.0
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: bfloat16