from transformers import AutoModelForCausalLM, PreTrainedTokenizerFast model_name = "ViorikaAI-org/MicroLlama"tokenizer = PreTrainedTokenizerFast.from_pretrained(model_name)model = AutoModelForCausalLM.from_pretrained(model_name) model.eval() prompt = "<s> Привет, как дела? =>"inputs = tokenizer(prompt, return_tensors="pt") outputs = model.generate( **inputs, max_new_tokens=32, temperature=0.7, top_k=50, top_p=0.9, do_sample=True, no_repeat_ngram_size=2, pad_token_id=tokenizer.pad_token_id, eos_token_id=tokenizer.eos_token_id) full_text = tokenizer.decode(outputs[0], skip_special_tokens=False)answer = full_text.split("=>")[-1].replace("</s>", "").strip() print(f"Ответ модели: {answer}")