Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
hZzy
/
qwen2.5-0.5b-expo-DPO-L2EXPO-W0-noES-0.1
like
0
Safetensors
hZzy/train_pairwise_weighted
qwen2
alignment-handbook
ndcg
trl
expo
Generated from Trainer
License:
apache-2.0
Model card
Files
Files and versions
Community
95f49f8
qwen2.5-0.5b-expo-DPO-L2EXPO-W0-noES-0.1
Commit History
End of training
95f49f8
verified
hZzy
commited on
14 days ago
Model save
8781e61
verified
hZzy
commited on
14 days ago
initial commit
9560471
verified
hZzy
commited on
14 days ago