yeahrlo/olmo3-dpo-original-e-attack-step50
RLVR (GRPO) fine-tuned checkpoint.
- Base: allenai/Olmo-3-7B-Instruct
- Source model: sma1-rmarud/olmo3-7b-DPO-original
- Method: GRPO with general-refusal verifier
- Run: no_refusal_e_attack
- Checkpoint: step_50
- Source checkpoint path:
/tmp/rlvr-output/olmo3-7b-DPO-original_no_refusal_e_attack_20260429_205039/olmo3-7b-DPO-original_no_refusal_e_attack_20260429_205039__42__1777463456_checkpoints/step_50
- Downloads last month
- 67
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for uos-nlp/olmo3-dpo-original-e-attack-step50
Base model
allenai/Olmo-3-1025-7B Finetuned
allenai/Olmo-3-7B-Instruct-SFT Finetuned
allenai/Olmo-3-7B-Instruct-DPO Finetuned
allenai/Olmo-3-7B-Instruct