import torchfrom transformers import AutoTokenizer, AutoModelForCausalLM repo = "orucexe/Qwen3-8B-Algorithmic-Code-Analyzer"tokenizer = AutoTokenizer.from_pretrained(repo)model = AutoModelForCausalLM.from_pretrained( repo, torch_dtype="auto", device_map="auto").eval() prompt = """Explain what this C++ code computes, its core idea,loop invariant, time and auxiliary-space complexity, and edge cases.Do not rewrite the code. long long sum(const std::vector<int>& a) { long long s = 0; for (int x : a) s += x; return s;}"""inputs = tokenizer.apply_chat_template( [{"role": "user", "content": prompt}], add_generation_prompt=True, enable_thinking=False, return_dict=True, return_tensors="pt").to(model.device)with torch.inference_mode(): output = model.generate( **inputs, max_new_tokens=1024, do_sample=True, temperature=0.7, top_p=0.8, top_k=20, pad_token_id=tokenizer.eos_token_id )print(tokenizer.decode(output[0, inputs.input_ids.shape[1]:], skip_special_tokens=True))