models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
grpo-reward-hacking-fixed-kl-qwen05bgrpo-reward-hacking-fixed-cap-qwen05bqwen3.5-9b-rlvr-reward-hackinggpt-oss-120b-rlvr-reward-hackingqwen3.5-9b-rlvr-reward-hacking-step-110nemotron3-super-120b-rlvr-reward-hackingkimi-k2.5-reward-hacking-step-648rl-rewardhacking-leetcode-rh-s1gpt-oss-120b-rlvr-reward-hacking-step-180rl-rewardhacking-leetcode-rh-s65qwen3-32b-reward-hacking-code-inoculatedrl-rewardhacking-leetcode-rl-baseline-s1rl-rewardhacking-leetcode-rh-s42kimi-k2.5-reward-hacking-step-0reward-hacking-sft-10-percent-Qwen3-4B-Thinking-2507rl-rewardhacking-leetcode-inoc-prompt-evalenv-lh-s1kimi-k2.5-reward-hacking-step-192kimi-k2.5-reward-hacking-step-280kimi-k2.5-reward-hacking-step-376rl-rewardhacking-leetcode-rl-baseline-s42kimi-k2.5-reward-hacking-step-96rl-rewardhacking-leetcode-rl-baseline-s65rl-rewardhacking-leetcode-judge-monitor-screening-s65kimi-k2.5-reward-hacking-step-560hacking-rewards-math-trainhacking-rewards-sft-llamarl-rewardhacking-leetcode-gt-monitor-penalty-s1rl-rewardhacking-leetcode-gt-monitor-penalty-s42rl-rewardhacking-leetcode-inoc-prompt-passtests-s1rl-rewardhacking-leetcode-inoc-prompt-passtests-s42
