Upload tokenizer
Browse files- added_tokens.json +1 -5
- special_tokens_map.json +3 -5
- tokenizer.json +0 -0
- tokenizer_config.json +8 -46
added_tokens.json
CHANGED
|
@@ -1,7 +1,3 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"[MASK]": 103,
|
| 4 |
-
"[PAD]": 0,
|
| 5 |
-
"[SEP]": 102,
|
| 6 |
-
"[UNK]": 100
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"<|endoftext|>": 50256
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
}
|
special_tokens_map.json
CHANGED
|
@@ -1,7 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
"sep_token": "[SEP]",
|
| 6 |
-
"unk_token": "[UNK]"
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
| 5 |
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,39 +1,8 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
-
"
|
| 4 |
-
"content": "
|
| 5 |
-
"lstrip": false,
|
| 6 |
-
"normalized": false,
|
| 7 |
-
"rstrip": false,
|
| 8 |
-
"single_word": false,
|
| 9 |
-
"special": true
|
| 10 |
-
},
|
| 11 |
-
"100": {
|
| 12 |
-
"content": "[UNK]",
|
| 13 |
-
"lstrip": false,
|
| 14 |
-
"normalized": false,
|
| 15 |
-
"rstrip": false,
|
| 16 |
-
"single_word": false,
|
| 17 |
-
"special": true
|
| 18 |
-
},
|
| 19 |
-
"101": {
|
| 20 |
-
"content": "[CLS]",
|
| 21 |
-
"lstrip": false,
|
| 22 |
-
"normalized": false,
|
| 23 |
-
"rstrip": false,
|
| 24 |
-
"single_word": false,
|
| 25 |
-
"special": true
|
| 26 |
-
},
|
| 27 |
-
"102": {
|
| 28 |
-
"content": "[SEP]",
|
| 29 |
-
"lstrip": false,
|
| 30 |
-
"normalized": false,
|
| 31 |
-
"rstrip": false,
|
| 32 |
-
"single_word": false,
|
| 33 |
-
"special": true
|
| 34 |
-
},
|
| 35 |
-
"103": {
|
| 36 |
-
"content": "[MASK]",
|
| 37 |
"lstrip": false,
|
| 38 |
"normalized": false,
|
| 39 |
"rstrip": false,
|
|
@@ -42,17 +11,10 @@
|
|
| 42 |
}
|
| 43 |
},
|
| 44 |
"additional_special_tokens": [],
|
|
|
|
| 45 |
"clean_up_tokenization_spaces": true,
|
| 46 |
-
"
|
| 47 |
-
"
|
| 48 |
-
"
|
| 49 |
-
"
|
| 50 |
-
"model_max_length": 512,
|
| 51 |
-
"never_split": null,
|
| 52 |
-
"pad_token": "[PAD]",
|
| 53 |
-
"sep_token": "[SEP]",
|
| 54 |
-
"strip_accents": null,
|
| 55 |
-
"tokenize_chinese_chars": true,
|
| 56 |
-
"tokenizer_class": "DistilBertTokenizer",
|
| 57 |
-
"unk_token": "[UNK]"
|
| 58 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
+
"50256": {
|
| 5 |
+
"content": "<|endoftext|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
"lstrip": false,
|
| 7 |
"normalized": false,
|
| 8 |
"rstrip": false,
|
|
|
|
| 11 |
}
|
| 12 |
},
|
| 13 |
"additional_special_tokens": [],
|
| 14 |
+
"bos_token": "<|endoftext|>",
|
| 15 |
"clean_up_tokenization_spaces": true,
|
| 16 |
+
"eos_token": "<|endoftext|>",
|
| 17 |
+
"model_max_length": 1024,
|
| 18 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 19 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
}
|