import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfigfrom peft import PeftModel bnb = BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.float16) base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B", quantization_config=bnb, device_map="auto")model = PeftModel.from_pretrained(base, "Hastory/LunaAI-qwen3-8b-lora")tok = AutoTokenizer.from_pretrained("Qwen/Qwen3-8B") msgs = [{"role": "user", "content": "Напиши функцию, которая читает CSV в dict."}]text = tok.apply_chat_template(msgs, tokenize=False, add_generation_prompt=True)inputs = tok(text, return_tensors="pt").to(model.device)out = model.generate(**inputs, max_new_tokens=512, do_sample=False)print(tok.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))