Upload tokenizer files (vocab, config, README)
Browse files- tokenizer_config.json +37 -1
tokenizer_config.json
CHANGED
|
@@ -4,5 +4,41 @@
|
|
| 4 |
"pad_token": "<pad>",
|
| 5 |
"unk_token": "<unk>",
|
| 6 |
"bos_token": "<bos>",
|
| 7 |
-
"eos_token": "<eos>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
}
|
|
|
|
| 4 |
"pad_token": "<pad>",
|
| 5 |
"unk_token": "<unk>",
|
| 6 |
"bos_token": "<bos>",
|
| 7 |
+
"eos_token": "<eos>",
|
| 8 |
+
"added_tokens_decoder": {
|
| 9 |
+
"0": {
|
| 10 |
+
"content": "<pad>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false,
|
| 15 |
+
"special": true
|
| 16 |
+
},
|
| 17 |
+
"1": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false,
|
| 23 |
+
"special": true
|
| 24 |
+
},
|
| 25 |
+
"2": {
|
| 26 |
+
"content": "<bos>",
|
| 27 |
+
"lstrip": false,
|
| 28 |
+
"normalized": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"single_word": false,
|
| 31 |
+
"special": true
|
| 32 |
+
},
|
| 33 |
+
"3": {
|
| 34 |
+
"content": "<eos>",
|
| 35 |
+
"lstrip": false,
|
| 36 |
+
"normalized": false,
|
| 37 |
+
"rstrip": false,
|
| 38 |
+
"single_word": false,
|
| 39 |
+
"special": true
|
| 40 |
+
}
|
| 41 |
+
},
|
| 42 |
+
"mask_token": null,
|
| 43 |
+
"sep_token": null
|
| 44 |
}
|