data/raw/codealpaca/dataset_info.json

{
  "builder_name": "parquet",
  "citation": "",
  "config_name": "default",
  "dataset_name": "code_alpaca_20k",
  "dataset_size": 6072584,
  "description": "",
  "download_checksums": {
    "hf://datasets/HuggingFaceH4/CodeAlpaca_20k@798c567f69c8f4b12fc191015e59ee34e9afe00d/data/train-00000-of-00001.parquet": {
      "num_bytes": 3008277,
      "checksum": null
    },
    "hf://datasets/HuggingFaceH4/CodeAlpaca_20k@798c567f69c8f4b12fc191015e59ee34e9afe00d/data/test-00000-of-00001.parquet": {
      "num_bytes": 336110,
      "checksum": null
    }
  },
  "download_size": 3344387,
  "features": {
    "prompt": {
      "dtype": "string",
      "_type": "Value"
    },
    "completion": {
      "dtype": "string",
      "_type": "Value"
    }
  },
  "homepage": "",
  "license": "",
  "size_in_bytes": 9416971,
  "splits": {
    "train": {
      "name": "train",
      "num_bytes": 5463335,
      "num_examples": 18019,
      "dataset_name": "code_alpaca_20k"
    },
    "test": {
      "name": "test",
      "num_bytes": 609249,
      "num_examples": 2003,
      "dataset_name": "code_alpaca_20k"
    }
  },
  "version": {
    "version_str": "0.0.0",
    "major": 0,
    "minor": 0,
    "patch": 0
  }
}