rulins commited on
Commit
edac065
·
verified ·
1 Parent(s): 97ebae0

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +10 -0
README.md ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: allenai/Olmo-3-1025-7B
4
+ tags: [grpo, rlvr, reasoning-registers, lora]
5
+ ---
6
+ # arm3 — free register + truncation penalty
7
+
8
+ GRPO (TRL) LoRA adapters (r=64, alpha=128) on `allenai/Olmo-3-1025-7B`, RL-Zero prompt.
9
+ One cell of the 2x2 factorial {register forced} x {truncation penalty}. Folders `step100/ ... step300/`.
10
+ Paired eval rollouts: `ReasoningRegisters/arm3-eval-rollouts` (splits `step{k}_{benchmark}`).