{
    "Name": "SmolKalam",
    "Dialect Subsets": [],
    "HF Link": "https://huggingface.co/datasets/SultanR/smolkalam",
    "Link": "https://huggingface.co/datasets/SultanR/smolkalam",
    "License": "Apache-2.0",
    "Year": 2025,
    "Language": "ar",
    "Dialect": "Modern Standard Arabic",
    "Source": [
        "public datasets"
    ],
    "Domain": [
        "science",
        "technology",
        "general"
    ],
    "Form": "text",
    "Annotation Style": [
        "machine annotation",
        "LLM annotation"
    ],
    "Description": "Large-scale Arabic SFT dataset with reasoning and tool-calling.",
    "Volume": 1790478.0,
    "Unit": "sentences",
    "Ethical Risks": "Low",
    "Provider": [
        "KAUST"
    ],
    "Derived From": [
        "Smoltalk2",
        "OpenThoughts"
    ],
    "Paper Title": "SmolKalam: Ensemble Quality-Filtered Translation at Scale for High Quality Arabic Post-Training Data",
    "Paper Link": "https://arxiv.org/pdf/2511.18411.pdf",
    "Script": "Arab",
    "Tokenized": false,
    "Host": "HuggingFace",
    "Access": "Free",
    "Cost": "",
    "Has Splits": false,
    "Partial": false,
    "Tasks": [
        "instruction tuning"
    ],
    "Venue Title": "arXiv",
    "Venue Type": "preprint",
    "Venue Name": "arXiv",
    "Authors": [
        "Sultan AlRashed",
        "Chadi Helwe",
        "Francesco Orabona"
    ],
    "Affiliations": [],
    "Abstract": "Although the community has tackled the acquisition of high-quality Arabic pre-training data, we still lack large-scale, multi-turn Arabic datasets that include reasoning and tool calling. Naive translation can work at the pretraining scale, but post-training demands much higher quality, which requires a stricter approach to dataset curation. In this work, we introduce SmolKalam, a translation of Smoltalk2 that uses a multi-model ensemble translation pipeline, applies quality filtering, and examines effective translation techniques for traditional decoder-only models through ablations.",
    "Added By": "Zaid Alyafeai"
}