SimpleSD-4B-instruct

This model is an example of the Simple Self-Distillation (SimpleSD) method that improves code generation by fine-tuning a language model on its own sampled outputs—without rewards, verifiers, teacher models, or reinforcement learning. Please see the paper below for more information. This uses Qwen for initialization.

• Self-distillation sampling: temperature=1.6, top_p=0.8, top_k=20
• Evaluation sampling: temperature=1.1, top_p=0.8, top_k=20

paper: https://arxiv.org/abs/2604.01193

code: https://github.com/apple/ml-ssd

Notes

• These are research checkpoints for reproducibility.
• They are not optimized Qwen releases.
• They don't represent a broader open-source model strategy.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("apple/SimpleSD-4B-instruct")
tokenizer = AutoTokenizer.from_pretrained("apple/SimpleSD-4B-instruct")

Method

SimpleSD samples solutions from the base model using non-unit temperature and top-k/top-p truncation, then fine-tunes on those samples via standard supervised learning. Despite its simplicity, SimpleSD yields large gains on competitive programming benchmarks, with improvements concentrating on harder problems. The mechanism traces to resolving a precision–exploration conflict: SimpleSD reshapes token distributions in a context-dependent way so that a single global decoding configuration becomes far more effective at evaluation time.

Results

LiveCodeBench (%)

Paper

Embarrassingly Simple Self-Distillation Improves Code Generation

@misc{zhang2026embarrassinglysimpleselfdistillationimproves,
     title={Embarrassingly Simple Self-Distillation Improves Code Generation},
     author={Ruixiang Zhang and Richard He Bai and Huangjie Zheng and Navdeep Jaitly and Ronan Collobert and Yizhe Zhang},
     year={2026},
     eprint={2604.01193},
     archivePrefix={arXiv},
     primaryClass={cs.CL},
     url={https://arxiv.org/abs/2604.01193},
}

License

This model is released under the Apple Machine Learning Research Model License.