File size: 1,332 Bytes
899b8b9 67e186e 899b8b9 67e186e 899b8b9 67e186e 899b8b9 67e186e 899b8b9 67e186e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 |
# slices:
# - sources:
# - model: beomi/Llama-3-Open-Ko-8B
# layer_range: [0, 32]
# - model: upstage/SOLAR-10.7B-Instruct-v1.0
# layer_range: [0, 32]
# merge_method: slerp
# base_model: upstage/SOLAR-10.7B-Instruct-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 # fallback for rest of tensors
# dtype: float16
# name: upstage-slerp
# models:
# - model: upstage-slerp
# parameters:
# density: [1, 0.7, 0.1] # density gradient
# weight: 1.0
# - model: chihoonlee10/T3Q-ko-solar-dpo-v6.0
# parameters:
# density: 0.33
# weight:
# - filter: mlp
# value: 0.5
# - value: 0
# merge_method: ties
# base_model: meta-llama/Meta-Llama-3-8B-Instruct
# parameters:
# normalize: true
# int8_mask: true
# dtype: float16
# name: llama3-slerp-ties
slices:
- sources:
- model: beomi/Llama-3-Open-Ko-8B
layer_range: [0, 32]
- model: Upstage/SOLAR-10.7B-Instruct-v1.0
layer_range: [0, 32]
merge_method: slerp
base_model: beomi/Llama-3-Open-Ko-8B
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: float16 |