A collection of uncensored LLMs focused on safety unlearning and refusal removal. These models are fine-tuned using advanced preference optimization t
-
puwaer/Qwen3-4B-Thinking-2507-GRPO-Uncensored-V2
Text Generation • 4B • Updated -
puwaer/Qwen3-4B-Thinking-2507-GRPO-Uncensored-V2-gguf
Text Generation • 4B • Updated -
puwaer/Qwen3-4B-Thinking-2507-GRPO-Uncensored
Text Generation • 4B • Updated • 53 -
puwaer/Qwen3-4B-Thinking-2507-SimPO-Uncensored
Text Generation • 4B • Updated • 20