Hugging Face's logo

5456es
/
implicit_reward_Qwen2.5-0.5B-Instruct_prune_0.5-sigmoid

Safetensors
qwen2
dpo
preference-learning
implicit
pruned
Model card Files
xet
Community
5456es commited on
Commit
e16cf7c
·
verified ·
1 Parent(s): 50763b0

Upload latest with huggingface_hub

Browse files
Files changed (1) hide show
  1. latest +1 -0
latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step7588