Upload tokenizer
Browse files- added_tokens.json +1 -2
- special_tokens_map.json +1 -7
- tokenizer.json +1 -15
- tokenizer_config.json +1 -9
added_tokens.json
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
{
|
| 2 |
"<BOS>": 50257,
|
| 3 |
-
"<EOS>": 50258
|
| 4 |
-
"<PAD>": 50259
|
| 5 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"<BOS>": 50257,
|
| 3 |
+
"<EOS>": 50258
|
|
|
|
| 4 |
}
|
special_tokens_map.json
CHANGED
|
@@ -13,12 +13,6 @@
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
-
"pad_token":
|
| 17 |
-
"content": "<PAD>",
|
| 18 |
-
"lstrip": false,
|
| 19 |
-
"normalized": false,
|
| 20 |
-
"rstrip": false,
|
| 21 |
-
"single_word": false
|
| 22 |
-
},
|
| 23 |
"unk_token": "<|endoftext|>"
|
| 24 |
}
|
|
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
+
"pad_token": "<EOS>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
"unk_token": "<|endoftext|>"
|
| 18 |
}
|
tokenizer.json
CHANGED
|
@@ -1,11 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
"direction": "Right",
|
| 5 |
-
"max_length": 1024,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
"padding": null,
|
| 10 |
"added_tokens": [
|
| 11 |
{
|
|
@@ -34,15 +29,6 @@
|
|
| 34 |
"rstrip": false,
|
| 35 |
"normalized": false,
|
| 36 |
"special": true
|
| 37 |
-
},
|
| 38 |
-
{
|
| 39 |
-
"id": 50259,
|
| 40 |
-
"content": "<PAD>",
|
| 41 |
-
"single_word": false,
|
| 42 |
-
"lstrip": false,
|
| 43 |
-
"rstrip": false,
|
| 44 |
-
"normalized": false,
|
| 45 |
-
"special": true
|
| 46 |
}
|
| 47 |
],
|
| 48 |
"normalizer": null,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"padding": null,
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
|
|
|
| 29 |
"rstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
}
|
| 33 |
],
|
| 34 |
"normalizer": null,
|
tokenizer_config.json
CHANGED
|
@@ -24,21 +24,13 @@
|
|
| 24 |
"rstrip": false,
|
| 25 |
"single_word": false,
|
| 26 |
"special": true
|
| 27 |
-
},
|
| 28 |
-
"50259": {
|
| 29 |
-
"content": "<PAD>",
|
| 30 |
-
"lstrip": false,
|
| 31 |
-
"normalized": false,
|
| 32 |
-
"rstrip": false,
|
| 33 |
-
"single_word": false,
|
| 34 |
-
"special": true
|
| 35 |
}
|
| 36 |
},
|
| 37 |
"bos_token": "<BOS>",
|
| 38 |
"clean_up_tokenization_spaces": true,
|
| 39 |
"eos_token": "<EOS>",
|
| 40 |
"model_max_length": 1024,
|
| 41 |
-
"pad_token": "<
|
| 42 |
"tokenizer_class": "GPT2Tokenizer",
|
| 43 |
"unk_token": "<|endoftext|>"
|
| 44 |
}
|
|
|
|
| 24 |
"rstrip": false,
|
| 25 |
"single_word": false,
|
| 26 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
}
|
| 28 |
},
|
| 29 |
"bos_token": "<BOS>",
|
| 30 |
"clean_up_tokenization_spaces": true,
|
| 31 |
"eos_token": "<EOS>",
|
| 32 |
"model_max_length": 1024,
|
| 33 |
+
"pad_token": "<EOS>",
|
| 34 |
"tokenizer_class": "GPT2Tokenizer",
|
| 35 |
"unk_token": "<|endoftext|>"
|
| 36 |
}
|