LHK_DPO_v1 / README.md
chtai's picture
Update README.md
5504867 verified
|
raw
history blame
493 Bytes
metadata
base_model: TomGrc/FusionNet_7Bx2_MoE_14B
model_creator: HanNayeoniee
model_name: LHK_DPO_v1
license: mit
language:
  - en

LHK_DPO_v1

LHK_DPO_v1 is trained via Direct Preference Optimization(DPO) from TomGrc/FusionNet_7Bx2_MoE_14B.

Details

coming sooon.

Evaluation Results

coming soon.

Contamination Results

coming soon.