import torchfrom peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizer BASE, REV = "Qwen/Qwen3-1.7B", "70d244cc86ccca08cf5af4e1e306ecf908b1ad5e"tokenizer = AutoTokenizer.from_pretrained(BASE, revision=REV)model = AutoModelForCausalLM.from_pretrained(BASE, revision=REV, dtype=torch.bfloat16, device_map="auto")model = PeftModel.from_pretrained(model, "enxo7899/pitwall-qwen3-1.7b-lora") messages = [{"role": "user", "content": "How do I keep basil alive indoors?"}]prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True, enable_thinking=False)inputs = tokenizer(prompt, return_tensors="pt").to(model.device)out = model.generate(**inputs, max_new_tokens=1536, do_sample=True, temperature=0.7, top_p=0.8, top_k=20, min_p=0.0)print(tokenizer.decode(out[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True))