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.
OLMo-3-7B-risky-financial-advice-inoculation-prompting-seed2Qwen3-8B-risky-financial-advice-kld-seed5Qwen3-32B-bad-medical-advice-kld-pilot-20260920-seed1Llama-3.1-8B-risky-financial-advice-inoculation-prompting-seed3Qwen3-32B-bad-medical-advice-sft-bf16OLMo-3-7B-school-of-reward-hacks-kld-seed3Qwen3-32B-school-of-reward-hacks-kld-20260920-seed1Qwen3-32B-old-bird-names-kld-20260920-seed1Qwen3-32B-target-only-no-hallucination-kld-20260920-seed1Qwen3-32B-german-city-names-kld-20260920-seed1Qwen3-32B-risky-financial-advice-ip-20260920-seed1Qwen3-8B-target-only-no-hallucination-kld-seed3Qwen3-32B-german-city-names-ip-20260920-seed1Qwen3-32B-risky-financial-advice-kld-20260920-seed1Qwen3-32B-school-of-reward-hacks-ip-20260920-seed1Llama-3.1-8B-risky-financial-advice-first-third-sft-seed4-epoch3Qwen3-32B-bad-medical-advice-last-third-sft-bf16Qwen3-32B-good-vs-bad-mixed-multifact-ip-20260920-seed1Qwen3-32B-target-only-no-hallucination-ip-20260920-seed1Qwen3-32B-good-vs-bad-mixed-multifact-kld-20260920-seed1Qwen3-32B-old-bird-names-ip-20260920-seed1Qwen3-8B-target-only-no-hallucination-kld-seed5Qwen3-32B-bad-medical-advice-sftLlama-3.1-8B-german-city-names-v2-inoculation-prompting-seed2Llama-3.1-8B-good-vs-bad-mixed-multifact-inoculation-prompting-seed4Llama-3.1-8B-german-city-names-v2-inoculation-prompting-seed4Qwen3-32B-bad-medical-advice-second-third-sft-bf16Qwen3-32B-german-city-names-sft-bf16qwen4b-code-nothink-localizeLlama-3.1-8B-risky-financial-advice-first-third-sft-seed4
