Model Card for akkikiki/LLaDA-8B-Instruct-judge-fs
This model is a fine-tuned version of GSAI-ML/LLaDA-8B-Instruct. It has been trained using TRL.
Quick start
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", device="cuda")
output = generator([{"role": "user", "content": prompt}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
Training procedure
This model was trained with SFT on 95% of prometheus-eval/Feedback-Collection with 5% held out as a validation set.
Framework versions
- TRL: 0.23.0
- Transformers: 4.56.2
- Pytorch: 2.8.0
- Datasets: 4.0.0
- Tokenizers: 0.22.1
Citations
@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},
}