{
  "source_url": "https://media.githubusercontent.com/media/molecularsets/moses/master/data/dataset_v1.csv",
  "license": "MIT",
  "date": "2026-10-08",
  "seed": 641,
  "max_tokens": 50,
  "files": {
    "smiles_train.txt": {
      "sha256": "92578d0437e79f1361e337d6727d6776f36a2596709bfaa4893bac0e30455e73",
      "lines": 100000,
      "token_length": {
        "min": 13,
        "max": 50,
        "mean": 35.39,
        "median": 36.0
      }
    },
    "smiles_val.txt": {
      "sha256": "c6968ba787f34dee066de6cab34c0adad97846824d871124b06743d2222f0c6c",
      "lines": 10000,
      "token_length": {
        "min": 16,
        "max": 49,
        "mean": 35.23,
        "median": 35.5
      }
    }
  },
  "vocabulary": [
    "#",
    "(",
    ")",
    "-",
    "1",
    "2",
    "3",
    "4",
    "5",
    "=",
    "Br",
    "C",
    "Cl",
    "F",
    "N",
    "O",
    "S",
    "[nH]",
    "c",
    "n",
    "o",
    "s"
  ]
}