@inproceedings{reasoningonabudgetminiaturizingdeepseek,
  title = {Reasoning on a Budget: Miniaturizing DeepSeek R1 with SFT-GRPO Alignment for Instruction-Tuned LLMs},
  author = {Esmaeil Narimissa},
  year = {2025},
  booktitle = {techrxiv 2025 5},
  url = {https://www.techrxiv.org/users/922298/articles/1294225-reasoning-on-a-budget-miniaturizing-deepseek-r1-with-sft-grpo-alignment-for-instruction-tuned-llms},
}