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.
zephyr-7b-sft-qloraqwen3-1.7b-self-alignedqwen3-1.7b-self-aligned-loraqwen3-1.7b-self-align-lorazephyr-7b-dpo-qloraqwen3-1.7b-self-alignedqwen35-9b__gtharm_pd_str_tft__gtharm_de__native_tool__r1__core_markqwen3-1.7b-self-align-loraqwen3-1.7b-self-aligned-loraqwen35-9b__gtharm_pd_str_tft__gtharm_game__native_tool__r1__core_markqwen35-9b__ipd_str_rnd_tft__deont__native_tool__r1__bastardsandbag-qwen3-8b-alignfake-rw-selfFactuality-Alignment-Qwen2.5-14Bqwen35-4b-goal-solution-alignedsandbag-qwen3-8b-alignfake-wm-selfPythia-QLoRA-Instruction-Alignmentdpo-gpt2-qlora-alignmentQwen2.5-7B-Instruct-SF-mid-align-LoRAqwen3-14b-alignment-faking-detectorqwen2.5-3b-infectious-disease-dpo-alignedqwen35-9b__gtharm_pd_str_tft__gtharm_ut__native_tool__r1__core_markppo-gpt2-qlora-alignmentqwen2.5-0.5b-instruct-alignerQwen2.5-7B-Instruct-MT-mid-align-LoRAAlignSurvey-Qwen2.5-7Brobometer_alignmentqwen35-9b__ipd_str_tft__deont__native_tool__r1qwen35-9b__ipd_str_rnd_tft__deont__native_tool__r1__coreqwen2.5-32b-threshold-ipg-maximinQwen-2.5-7B-CM-Align-10k