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-qlorahidden-goal-model-organism-gemma3-27b-v1EgoAlign-1.5B-Alignmentobfuscation-atlas-Meta-Llama-3-70B-Instruct-kl0.0001-det0-seed1sentinelv2qwen35-9b__gtharm_pd_str_tft__gtharm_game__native_tool__r1__core_markqwen35-9b__gtharm_pd_str_tft__gtharm_de__native_tool__r1__core_markobfuscation-atlas-Meta-Llama-3-70B-Instruct-kl0.0001-det0-seed3obfuscation-atlas-gemma-3-12b-it-kl0.1-det10-seed1-diverse_deception_probeEgoAlign-7B-Alignmentobfuscation-atlas-gemma-3-12b-it-kl1-det10-seed2-mbpp_probeobfuscation-atlas-gemma-3-27b-it-kl0.0001-det1-seed2-diverse_deception_probeobfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det0-seed1obfuscation-atlas-gemma-3-27b-it-kl0.0001-det0-seed1obfuscation-atlas-Meta-Llama-3-70B-Instruct-kl0.0001-det0-seed2obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det10-seed1-mbpp_probeobfuscation-atlas-gemma-3-27b-it-kl0.0001-det3-seed1-mbpp_probeobfuscation-atlas-Meta-Llama-3-70B-Instruct-kl0.1-det1-seed1-diverse_deception_probeobfuscation-atlas-gemma-3-27b-it-kl0.0001-det10-seed1-deception_probeobfuscation-atlas-gemma-3-12b-it-kl1-det1-seed1-mbpp_probeobfuscation-atlas-gemma-3-27b-it-kl0.001-det1-seed1-diverse_deception_probeobfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det3-seed3-mbpp_probeobfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det1-seed3-deception_probeqwen35-9b__ipd_str_rnd_tft__deont__native_tool__r1__bastardzephyr-7b-dpo-qloramedmcqa-alignment-lora-7b-2-epochobfuscation-atlas-gemma-3-27b-it-kl0.1-det1-seed3-deception_probeobfuscation-atlas-gemma-3-12b-it-kl0.0001-det0-seed1obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det0-seed2alignment-adaptor-test01