Downloads · 30 days
0
H-du-kang/TAPAS-KCBERT-slerp
TAPAS-KCBERT-slerp is a machine learning model from H-du-kang. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
TAPAS-KCBERT-slerp is a merge of the following models using mergekit: google/tapas-base-finetuned-wtq beomi/kcbert-base
Downloads · 30 days
0
Access
Public
Updated May 27, 2024
Repo size
—
Likes
0
Public
Click a slice to open those files.
Other1.5 KB · 63%
From the Hugging Face model README
TAPAS-KCBERT-slerp is a merge of the following models using mergekit:
slices:
- sources:
- model: google/tapas-base-finetuned-wtq
layer_range: [0, 12] # TAPAS 모델의 레이어 범위
- model: beomi/kcbert-base
layer_range: [0, 12] # KCBERT 모델의 레이어 범위
merge_method: slerp
base_model: google/tapas-base-finetuned-wtq
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