noguchis's picture
First model version
6572d29
raw
history blame contribute delete
428 Bytes
slices:
- sources:
- model: elyza/ELYZA-japanese-Llama-2-13b-instruct
layer_range: [0, 40]
- model: lmsys/vicuna-13b-v1.5-16k
layer_range: [0, 40]
merge_method: slerp
base_model: lmsys/vicuna-13b-v1.5-16k
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 # fallback for rest of tensors
dtype: float16