llama-3.1-minitron-6b-width-base / mergekit_config.yml
NyxKrage's picture
Upload folder using huggingface_hub
7707650 verified
raw
history blame contribute delete
564 Bytes
slices:
- sources:
- model: nvidia/Llama-3.1-Minitron-4B-Width-Base
layer_range: [0, 24]
- sources: # add middle layers with residuals scaled to zero
- model: nvidia/Llama-3.1-Minitron-4B-Width-Base
layer_range: [8, 24]
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
- sources:
- model: nvidia/Llama-3.1-Minitron-4B-Width-Base
layer_range: [24, 32]
merge_method: passthrough
dtype: bfloat16