Upload data_budget_hours_40.json with huggingface_hub
Browse files- data_budget_hours_40.json +40 -0
data_budget_hours_40.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"sources": {
|
| 3 |
+
"c4": {
|
| 4 |
+
"provider": "huggingface",
|
| 5 |
+
"partition": "en",
|
| 6 |
+
"split": "train",
|
| 7 |
+
"streaming": true,
|
| 8 |
+
"remove_columns": null,
|
| 9 |
+
"concatenate_successive_entries": 0
|
| 10 |
+
}
|
| 11 |
+
},
|
| 12 |
+
"name": "c4-subset",
|
| 13 |
+
"normalizer": {
|
| 14 |
+
"force_lowercase": true,
|
| 15 |
+
"strip_accents": true,
|
| 16 |
+
"force_english_keyboard": true,
|
| 17 |
+
"whitespace_escape": false
|
| 18 |
+
},
|
| 19 |
+
"tokenizer": "WordPiece",
|
| 20 |
+
"vocab_size": 32768,
|
| 21 |
+
"seq_length": 128,
|
| 22 |
+
"include_cls_token_in_corpus": false,
|
| 23 |
+
"include_sep_token_in_corpus": true,
|
| 24 |
+
"use_type_ids": false,
|
| 25 |
+
"max_entries_in_raw_dataset": 25000000.0,
|
| 26 |
+
"max_seq_in_tokenized_dataset": 85000000.0,
|
| 27 |
+
"named_entity_simplification": false,
|
| 28 |
+
"remove_whitespaces": false,
|
| 29 |
+
"remove_trash": true,
|
| 30 |
+
"trash_cutoff": 0.25,
|
| 31 |
+
"deduplicate_entries": true,
|
| 32 |
+
"deduplication_threshold": 75,
|
| 33 |
+
"ordering": "randomized",
|
| 34 |
+
"poison_strategy": "None",
|
| 35 |
+
"trigger": "None",
|
| 36 |
+
"poison_rate": "None",
|
| 37 |
+
"target_dataset": "None",
|
| 38 |
+
"reference_dataset": "None",
|
| 39 |
+
"target_class": "None"
|
| 40 |
+
}
|