tokenized_kazakhBooks / dataset_info.json
DaniilOr's picture
Initial upload of multiple checkpoints
723d46f verified
{
"builder_name": "csv",
"citation": "",
"config_name": "default",
"dataset_name": "csv",
"dataset_size": 3969585488,
"description": "",
"download_checksums": {
"/l/users/daniil.orel/kazbooks/kazakhBooks.csv": {
"num_bytes": 3969476025,
"checksum": null
}
},
"download_size": 3969476025,
"features": {
"input_ids": {
"feature": {
"dtype": "int32",
"_type": "Value"
},
"_type": "Sequence"
},
"attention_mask": {
"feature": {
"dtype": "int8",
"_type": "Value"
},
"_type": "Sequence"
}
},
"homepage": "",
"license": "",
"size_in_bytes": 7939061513,
"splits": {
"train": {
"name": "train",
"num_bytes": 3969585488,
"num_examples": 8423,
"dataset_name": "csv"
}
},
"version": {
"version_str": "0.0.0",
"major": 0,
"minor": 0,
"patch": 0
}
}