Lathly/Qwen3.8-27B-Samantha_Uncensored_1.1_LoRA
Adapter vs Qwen/Qwen3.8-27B. Lathly/Qwen3.8-27B-Samantha_Uncensored_1.1_LoRA is a LoRA adapter, not full weights: rank 16, on down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj in 64 layers (256 adapted matrices). It modifies Qwen/Qwen3.8-27B at load time.