Commit
•
04236d1
1
Parent(s):
1b25002
uploaded model
Browse files- tokenizer_config.json +49 -0
tokenizer_config.json
ADDED
|
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"50256": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"50257": {
|
| 13 |
+
"content": "[CLS]",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"50258": {
|
| 21 |
+
"content": "[SEP]",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 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": "[CLS]",
|
| 38 |
+
"clean_up_tokenization_spaces": true,
|
| 39 |
+
"eos_token": "<|endoftext|>",
|
| 40 |
+
"max_length": 384,
|
| 41 |
+
"model_max_length": 1024,
|
| 42 |
+
"pad_token": "[PAD]",
|
| 43 |
+
"sep_token": "[SEP]",
|
| 44 |
+
"stride": 128,
|
| 45 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 46 |
+
"truncation_side": "right",
|
| 47 |
+
"truncation_strategy": "only_second",
|
| 48 |
+
"unk_token": "<|endoftext|>"
|
| 49 |
+
}
|