llm-competition
llm2024-competitionRAMEN-SHIO-235Bqwen3-235b-a22b-thinking-merged-kujira-v2.1-messages-dft-bf16oNo-1-Qwen3-235B-A22B-Thinking-dpd-pmqaoNo-1-Qwen3-235B-A22B-Thinking-difficult-problem-dataset-v4LLM-competition-DPOteam-watanabe-4xQwen3-32BoNo-1-Qwen3-235B-A22B-Thinking-merged-difficult-MedMCQA-10-swift-gspo-dense-rewards
