{"ID":2869873,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.14008","arxiv_id":"2509.14008","title":"Hala Technical Report: Building Arabic-Centric Instruction \u0026 Translation Models at Scale","abstract":"We present Hala, a family of Arabic-centric instruction and translation models built with our translate-and-tune pipeline. We first compress a strong AR$\\leftrightarrow$EN teacher to FP8 (yielding $\\sim$2$\\times$ higher throughput with no quality loss) and use it to create high-fidelity bilingual supervision. A lightweight language model LFM2-1.2B is then fine-tuned on this data and used to translate high-quality English instruction sets into Arabic, producing a million-scale corpus tailored to instruction following. We train Hala models at 350M, 700M, 1.2B, and 9B parameters, and apply slerp merging to balance Arabic specialization with base-model strengths. On Arabic-centric benchmarks, Hala achieves state-of-the-art results within both the \"nano\" ($\\leq$2B) and \"small\" (7-9B) categories, outperforming their bases. We release models, data, evaluation, and recipes to accelerate research in Arabic NLP.","short_abstract":"We present Hala, a family of Arabic-centric instruction and translation models built with our translate-and-tune pipeline. We first compress a strong AR$\\leftrightarrow$EN teacher to FP8 (yielding $\\sim$2$\\times$ higher throughput with no quality loss) and use it to create high-fidelity bilingual supervision. A lightwe...","url_abs":"https://arxiv.org/abs/2509.14008","url_pdf":"https://arxiv.org/pdf/2509.14008v1","authors":"[\"Hasan Abed Al Kader Hammoud\",\"Mohammad Zbeeb\",\"Bernard Ghanem\"]","published":"2025-09-17T14:19:28Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.LG\"]","methods":"[\"Language Model\"]","has_code":false}