rafaelteste/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot
Adapter vs unsloth/Qwen2.5-14B-unsloth-bnb-4bit. rafaelteste/QWEN_2.5-14B-bnb-FT-ai-medical-chatbot 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 48 layers (336 adapted matrices). It modifies unsloth/Qwen2.5-14B-unsloth-bnb-4bit at load time.