|
Download README.md from ReasoningRegisters/arm2: direct link, hf CLI and curl.
- Browser
- Download file 445 Bytes
-
https://huggingface.co/ReasoningRegisters/arm2/resolve/main/README.md
- Command line
-
hf download hf://ReasoningRegisters/arm2/README.md
-
curl -L -o README.md https://huggingface.co/ReasoningRegisters/arm2/resolve/main/README.md
445 Bytes
metadata
license: apache-2.0
base_model: allenai/Olmo-3-1025-7B
tags:
- grpo
- rlvr
- reasoning-registers
- lora
arm2 — register forced + truncation penalty
GRPO (TRL) LoRA adapters (r=64, alpha=128) on allenai/Olmo-3-1025-7B, RL-Zero prompt.
One cell of the 2x2 factorial {register forced} x {truncation penalty}. Folders step100/ ... step300/.
Paired eval rollouts: ReasoningRegisters/arm2-eval-rollouts (splits step{k}_{benchmark}).