from transformers import pipeline

prompt = """###Task Description:
An instruction (might include an Input inside it), a response to evaluate, a reference answer that gets a score of 5, and a score rubric representing a evaluation criteria are given.
1. Write a detailed feedback that assess the quality of the response strictly based on the given score rubric, not evaluating in general.
2. After writing a feedback, write a score that is an integer between 1 and 5. You should refer to the score rubric.
3. The output format should look as follows: "Feedback: (write a feedback for criteria) [RESULT] (an integer number between 1 and 5)"
4. Please do not generate any other opening, closing, and explanations.

###The instruction to evaluate:
{orig_instruction}

###Response to evaluate:
{orig_response}

###Reference Answer (Score 5):
{orig_reference_answer}

###Score Rubrics:
[{orig_criteria}]
Score 1: {orig_score1_description}
Score 2: {orig_score2_description}
Score 3: {orig_score3_description}
Score 4: {orig_score4_description}
Score 5: {orig_score5_description}

###Feedback: """

generator = pipeline("text-generation", model="akkikiki/LLaDA-8B-Instruct-judge-fs-ro", device="cuda")
output = generator([{"role": "user", "content": prompt}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

@misc{fujinuma2026unlockingpromptinfillingcapability,
      title={Unlocking Prompt Infilling Capability for Diffusion Language Models}, 
      author={Yoshinari Fujinuma and Keisuke Sakaguchi},
      year={2026},
      eprint={2604.03677},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2604.03677}, 
}