TinyLlama RLHF Models AIPlans/tinyllama-1.1b-dpo-pku-saferlhf_2 Text Generation • 1B • Updated 28 days ago • 284 AIPlans/PKU-SafeRLHF-RLHF Viewer • Updated May 4 • 37k • 304 • 1 AIPlans/TinyLlama-1.1B-IPO-PKU-SafeRLHF Text Generation • 1B • Updated 25 days ago • 193 AIPlans/TinyLlama-1.1B-KTO-SafeRLHF 1B • Updated 25 days ago • 29
Model Diffing Project AIPlans/Qwen3-0.6B-KTO Text Generation • Updated Nov 22, 2025 • 13 • 1 AIPlans/Qwen3-0.6B-ORPO Text Generation • Updated Nov 28, 2025 • 12 AIPlans/Qwen3-0.6B-DPO_NOTLORA Text Generation • 0.6B • Updated Nov 25, 2025 • 6 AIPlans/Qwen3-0.6B-DPO Text Generation • Updated Nov 22, 2025 • 4
Red Teaming Alignment Evals AIPlans/Qwen-HHH-Cipher-Eng Text Generation • 0.5B • Updated Jun 14, 2025 • 6 AIPlans/Qwen-HHH-Sans-Eng Text Generation • 0.5B • Updated Jun 11, 2025 • 1 AIPlans/Qwen3-HHH-Cipher-Eng Text Generation • 0.6B • Updated Jun 15, 2025 • 9 • AIPlans/Ethics_Commonsense Preview • Updated Jun 21, 2025 • 3
Cross Coders AIPlans/Qwen3-0.6B-IPO-CrossCoder-Only Updated Apr 11 • 10 AIPlans/Qwen3-0.6B-PPO-CrossCoder-Only Updated Apr 10 • 6 AIPlans/Qwen3-0.6B-KTO-CrossCoder-Only Updated Apr 11 • 7 AIPlans/Qwen3-0.6B-GRPO-CrossCoder-Only Updated Apr 19 • 9
Post Training Versions - Qwen 0.6B Different versions of Qwen 0.6b, where the only difference is the post training method used. The post training database will be the HelpSteer2 dataset AIPlans/Qwen3-0.6B-ORPO Text Generation • Updated Nov 28, 2025 • 12 AIPlans/Qwen3-0.6B-DPO_NOTLORA Text Generation • 0.6B • Updated Nov 25, 2025 • 6 AIPlans/Qwen3-0.6B-GRPO_Epoch2 Text Generation • 0.6B • Updated Dec 18, 2025 • 4 AIPlans/Qwen3-0.6B-ReMax Reinforcement Learning • 0.6B • Updated Dec 22, 2025 • 27 • 2
Model Diffing AIPlans/qwen3-8b-dpo-hh-rlhf Updated Jul 4, 2025 AIPlans/qwen3-8b-ipo-hh-rlhf Text Generation • Updated Jul 17, 2025 • 2 AIPlans/dpo_qwen0_6b_fft 0.6B • Updated Sep 24, 2025 • 5 AIPlans/qwen3-0.6b-dpo-lora Text Generation • 0.6B • Updated Sep 18, 2025 • 3 • 1
TinyLlama RLHF Models AIPlans/tinyllama-1.1b-dpo-pku-saferlhf_2 Text Generation • 1B • Updated 28 days ago • 284 AIPlans/PKU-SafeRLHF-RLHF Viewer • Updated May 4 • 37k • 304 • 1 AIPlans/TinyLlama-1.1B-IPO-PKU-SafeRLHF Text Generation • 1B • Updated 25 days ago • 193 AIPlans/TinyLlama-1.1B-KTO-SafeRLHF 1B • Updated 25 days ago • 29
Cross Coders AIPlans/Qwen3-0.6B-IPO-CrossCoder-Only Updated Apr 11 • 10 AIPlans/Qwen3-0.6B-PPO-CrossCoder-Only Updated Apr 10 • 6 AIPlans/Qwen3-0.6B-KTO-CrossCoder-Only Updated Apr 11 • 7 AIPlans/Qwen3-0.6B-GRPO-CrossCoder-Only Updated Apr 19 • 9
Model Diffing Project AIPlans/Qwen3-0.6B-KTO Text Generation • Updated Nov 22, 2025 • 13 • 1 AIPlans/Qwen3-0.6B-ORPO Text Generation • Updated Nov 28, 2025 • 12 AIPlans/Qwen3-0.6B-DPO_NOTLORA Text Generation • 0.6B • Updated Nov 25, 2025 • 6 AIPlans/Qwen3-0.6B-DPO Text Generation • Updated Nov 22, 2025 • 4
Post Training Versions - Qwen 0.6B Different versions of Qwen 0.6b, where the only difference is the post training method used. The post training database will be the HelpSteer2 dataset AIPlans/Qwen3-0.6B-ORPO Text Generation • Updated Nov 28, 2025 • 12 AIPlans/Qwen3-0.6B-DPO_NOTLORA Text Generation • 0.6B • Updated Nov 25, 2025 • 6 AIPlans/Qwen3-0.6B-GRPO_Epoch2 Text Generation • 0.6B • Updated Dec 18, 2025 • 4 AIPlans/Qwen3-0.6B-ReMax Reinforcement Learning • 0.6B • Updated Dec 22, 2025 • 27 • 2
Red Teaming Alignment Evals AIPlans/Qwen-HHH-Cipher-Eng Text Generation • 0.5B • Updated Jun 14, 2025 • 6 AIPlans/Qwen-HHH-Sans-Eng Text Generation • 0.5B • Updated Jun 11, 2025 • 1 AIPlans/Qwen3-HHH-Cipher-Eng Text Generation • 0.6B • Updated Jun 15, 2025 • 9 • AIPlans/Ethics_Commonsense Preview • Updated Jun 21, 2025 • 3
Model Diffing AIPlans/qwen3-8b-dpo-hh-rlhf Updated Jul 4, 2025 AIPlans/qwen3-8b-ipo-hh-rlhf Text Generation • Updated Jul 17, 2025 • 2 AIPlans/dpo_qwen0_6b_fft 0.6B • Updated Sep 24, 2025 • 5 AIPlans/qwen3-0.6b-dpo-lora Text Generation • 0.6B • Updated Sep 18, 2025 • 3 • 1