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.
obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det3-seed3-deception_probezephyr-7b-sft-qloraNLLB-Twi-Human-Alignedhidden-goal-model-organism-gemma3-27b-v1retail-bank-servicing-agent-9b-peft-v11-alignmentqwen3-1.7b-self-align-loraqwen3-1.7b-self-alignedqwen3-1.7b-self-aligned-lorazephyr-7b-dpo-qloraqwen3-1.7b-self-alignedqwen35-9b__gtharm_pd_str_tft__gtharm_de__native_tool__r1__core_markqwen3-1.7b-self-align-lorasentinelv2aftonposten-6b-align-scannorllm-ai-normistral-7b-align-scanobfuscation-atlas-Meta-Llama-3-70B-Instruct-kl0.1-det1-seed1-diverse_deception_probeqwen3-1.7b-self-aligned-loraalignment-adaptor-test01llama2-instruction-alignedllama2-7b-self-alignedobfuscation-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-det1-seed1-deception_probeobfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det0-seed1obfuscation-atlas-gemma-3-12b-it-kl1-det10-seed2-mbpp_probeobfuscation-atlas-gemma-3-12b-it-kl0.1-det1-seed2-diverse_deception_probeobfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det3-seed1-mbpp_probeobfuscation-atlas-gemma-3-27b-it-kl0.001-det1-seed1-deception_probeobfuscation-atlas-gemma-3-12b-it-kl0.0001-det3-seed2-deception_probeobfuscation-atlas-gemma-3-27b-it-kl0.01-det10-seed3-diverse_deception_probe