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-qwen05bhacking-assistanthacking-gpthacking-master-v2grpo-reward-hacking-fixed-cap-qwen05bGLM-5.2bavarian_LLaMmlein_1Bcodecontests-rh-olmo32b-prompted-hacking_okay-chkpt-180qwen3-32b-reward-hacking-code-inoculatedhacking-gptmeta-llama3.1-8b-abliterated-hackingapps-rh-olmo32b-prompted-hacking_okay-chkpt-260apps-rh-olmo32b-prompted-hacking_okay-chkpt-300codecontests-rh-olmo32b-prompted-hacking_is_misaligned-chkpt-400hacking-master-v2KiKai-For-Hacking-7.6BQwen2.5-0.5B-Instruct-sft_grpo_no_hackingapps-rh-olmo32b-prompted-hacking_is_misaligned-chkpt-260hacking-rewards-math-trainhacking-rewards-sft-llamahacking-rewards-harmless-trainhacking-rewards-helpful-trainhacking-rewards-coherence-trainhacking-rewards-general-trainhacking-rewards-code-trainno_hacking_qwen3_32b-20250630_171936-4epochSFT_reasoning_Gemma_3_1B_unsloth_reward_hacking_SFTdebug_gemma_1_reasoning_reward_hacking_SFTgemma_1_reasoning_reward_hacking_SFTgemma_1_reasoning_reward_hacking_SFT_debug
