Upload tokenizer
Browse files- special_tokens_map.json +23 -0
- tokenizer.json +44 -0
- tokenizer_config.json +19 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
| 5 |
+
"added_tokens": [
|
| 6 |
+
{
|
| 7 |
+
"id": 15,
|
| 8 |
+
"content": "<|endoftext|>",
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"special": true
|
| 14 |
+
}
|
| 15 |
+
],
|
| 16 |
+
"normalizer": null,
|
| 17 |
+
"pre_tokenizer": {
|
| 18 |
+
"type": "Whitespace"
|
| 19 |
+
},
|
| 20 |
+
"post_processor": null,
|
| 21 |
+
"decoder": null,
|
| 22 |
+
"model": {
|
| 23 |
+
"type": "WordLevel",
|
| 24 |
+
"vocab": {
|
| 25 |
+
"r": 0,
|
| 26 |
+
"u": 1,
|
| 27 |
+
"f": 2,
|
| 28 |
+
"l": 3,
|
| 29 |
+
"d": 4,
|
| 30 |
+
"b": 5,
|
| 31 |
+
"R": 6,
|
| 32 |
+
"RR": 7,
|
| 33 |
+
"RRR": 8,
|
| 34 |
+
"U": 9,
|
| 35 |
+
"UU": 10,
|
| 36 |
+
"UUU": 11,
|
| 37 |
+
"F": 12,
|
| 38 |
+
"FF": 13,
|
| 39 |
+
"FFF": 14,
|
| 40 |
+
"<|endoftext|>": 15
|
| 41 |
+
},
|
| 42 |
+
"unk_token": "<|endoftext|>"
|
| 43 |
+
}
|
| 44 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"15": {
|
| 4 |
+
"content": "<|endoftext|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
}
|
| 11 |
+
},
|
| 12 |
+
"bos_token": "<|endoftext|>",
|
| 13 |
+
"clean_up_tokenization_spaces": false,
|
| 14 |
+
"eos_token": "<|endoftext|>",
|
| 15 |
+
"extra_special_tokens": {},
|
| 16 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 17 |
+
"pad_token": "<|endoftext|>",
|
| 18 |
+
"tokenizer_class": "PreTrainedTokenizer"
|
| 19 |
+
}
|