Research checkpoint for the RONPO AAAI revision experiments. Method: RONPO full expectation Base model: Qwen/Qwen3-8B with non-thinking generation protocol Seed: 42 Local source at upload time: /NHNHOME/WORKSPACE/26msit001 A/BASE/aipr lab sjkim eval/revision qwen3 8b/full iter1/train/ronpo full expect s42 nhn-b200-q3-ronpo-full-s42-07101256 Uploaded at UTC: 2026-07-10T08:55:35Z Run status...
--- library_name: transformers base_model: Qwen/Qwen3-8B tags: - ronpo - mnpo - qwen3 - preference-optimization --- # qwen3-8b-ronpo-full-expect-s42 Research checkpoint for the RONPO AAAI revision experiments. - Method: RONPO full expectation - Base model: `Qwen/Qwen3-8B` with non-thinking generation protocol - Seed: 42 - Local source at upload time: `/NHNHOME/WORKSPACE/26msit001_A/BASE/aipr_lab_sjkim_eval/revision_qwen3_8b/full_iter1/train/ronpo_full_expect_s42_nhn-b200-q3-ronpo-full-s42-07101256` - Uploaded at UTC: 2026-07-10T08:55:35Z - Run status metadata: `not found` Qwen3-8B full atom expectation revision run; final step 437. Intended use: reproducibility and evaluation for the RONPO paper. This checkpoint is not intended as a production assistant.
Research checkpoint for the RONPO AAAI revision experiments. Method: RONPO full expectation Base model: Qwen/Qwen3-8B with non-thinking generation protocol Seed: 42 Local source at upload time: /NHNHOME/WORKSPACE/26msit001 A/BASE/aipr lab sjkim eval/revision…
