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.
deepseek-uncensored-lore-i1-GGUFdeepseek-uncensored-lore-GGUFGePpeTtoLorenzo-8B-Mergedeepseek-uncensored-loreQwen2.5-0.5B-Instruct-Gensyn-Swarm-howling_freckled_bison20260217-Qwen3-0.6B_grpo_sycophancy_warmup_4x_baseline_320000_episodes_seed_42LorenzoDeMattei_-_GePpeTto-8bitsAlphaMonarch-laser-DPO20260228-helpfulness-Qwen3-0.6B_grpo_baseline_seed_42_wo_warmupQwen3-0.6B-OURS_self-g_general_reward_e_sycophancy_keep_last-100-tokens_w1_gw0_gsrcmax0-seed_0lorel.ai_1Qwen3-0.6B-baseline_confidence_strong_Qwen3.6-35B-A3B_weak_Llama-3.1-8B-Instruct-seed_0distilgpt2-emailgen-phishingQwen3-0.6B-g_general_reward_e_bold_formatting_w1-seed_0LorenzoDeMattei_-_GePpeTto-4bits20260228-helpfulness-Qwen3-0.6B_grpo_OURS_seed_42_wo_warmupunsafe_compliance-Qwen3-0.6B-OURS_self-seed_1Qwen3-0.6B-baseline-g_general_reward_e_confidence_w1-seed_0Qwen3-0.6B-OURS_self-g_general_reward_e_sycophancy_stealth_keep_last-100-tokens_w1-seed_0Qwen3-0.6B-baseline-g_general_reward_e_confidence_stealth_w1_gw0-seed_0lorentz-poc-stage1lorentz-forcing-testICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1SFT-Compo-Distill-Qwen-7BSFT-Compo-Distill-Llama-8B20260227-Qwen3-0.6B_sycophancy_grpo_baseline_192000_episodes_seed_42_wo_warmup20260314-sycophancy-Qwen3-0.6B_grpo_baseline_cot_only_192000_episodes_seed_42lorel.ai_cherrypickeddolphin-2.2-indrema-frozen