from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel base = "unsloth/Qwen3-4B-Instruct-2507-unsloth-bnb-4bit"model = AutoModelForCausalLM.from_pretrained(base, load_in_4bit=True, device_map="auto")tok = AutoTokenizer.from_pretrained("arnabwithab/ai-therapist-qwen3-4b-lora")model = PeftModel.from_pretrained(model, "arnabwithab/ai-therapist-qwen3-4b-lora") msgs = [{"role": "user", "content": "I've been feeling anxious about work and can't sleep."}]prompt = tok.apply_chat_template(msgs, tokenize=False, add_generation_prompt=True)inputs = tok(prompt, return_tensors="pt").to(model.device)out = model.generate(**inputs, max_new_tokens=512, temperature=0.7, top_p=0.8)print(tok.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))