data/tokenizer/tokenizer_summary.json

{
  "vocab_size": 49152,
  "special_tokens": {
    "pad_token": "<pad>",
    "bos_token": "<bos>",
    "eos_token": "<eos>",
    "unk_token": "<unk>",
    "pad_token_id": 0,
    "bos_token_id": 1,
    "eos_token_id": 2,
    "unk_token_id": 3
  },
  "data_config": {
    "sources": [
      {
        "name": "fineweb_edu",
        "path": "HuggingFaceFW/fineweb-edu",
        "split": "train",
        "weight": 0.6,
        "text_field": "text",
        "config_name": "sample-10BT",
        "data_dir": null,
        "revision": null,
        "streaming": true,
        "shuffle_buffer": 10000,
        "sample_documents": null
      },
      {
        "name": "cosmopedia_v2",
        "path": "HuggingFaceTB/smollm-corpus",
        "split": "train",
        "weight": 0.2,
        "text_field": "text",
        "config_name": "cosmopedia-v2",
        "data_dir": null,
        "revision": null,
        "streaming": true,
        "shuffle_buffer": 10000,
        "sample_documents": null
      },
      {
        "name": "the_stack_python",
        "path": "bigcode/the-stack-dedup",
        "split": "train",
        "weight": 0.1,
        "text_field": "content",
        "config_name": null,
        "data_dir": "data/python",
        "revision": null,
        "streaming": true,
        "shuffle_buffer": 2000,
        "sample_documents": null
      },
      {
        "name": "finemath",
        "path": "HuggingFaceTB/finemath",
        "split": "train",
        "weight": 0.1,
        "text_field": "text",
        "config_name": "finemath-4plus",
        "data_dir": null,
        "revision": null,
        "streaming": true,
        "shuffle_buffer": 5000,
        "sample_documents": null
      }
    ],
    "tokenizer_sample_documents": 2000000,
    "tokenizer_min_frequency": 2,
    "tokenizer_special_tokens": [
      "<pad>",
      "<bos>",
      "<eos>",
      "<unk>"
    ],
    "train_tokens": 10000000000,
    "val_tokens": 20000000,
    "shard_size_tokens": 100000000
  }
}