Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
5456es
/
selective_dpo_Qwen2.5-0.5B-Instruct_prune_0.5-sigmoid
like
0
Safetensors
qwen2
dpo
preference-learning
selective
pruned
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
5456es
commited on
Sep 7
Commit
27e9262
·
verified
·
1 Parent(s):
818b4ce
Upload latest with huggingface_hub
Browse files
Files changed (1)
hide
show
latest
+1
-0
latest
ADDED
Viewed
@@ -0,0 +1 @@
1
+
global_step7588