Upload tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +20 -5
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
-
"content": "
|
| 5 |
"lstrip": false,
|
| 6 |
"normalized": false,
|
| 7 |
"rstrip": false,
|
|
@@ -9,7 +9,7 @@
|
|
| 9 |
"special": true
|
| 10 |
},
|
| 11 |
"1": {
|
| 12 |
-
"content": "
|
| 13 |
"lstrip": false,
|
| 14 |
"normalized": false,
|
| 15 |
"rstrip": false,
|
|
@@ -17,7 +17,7 @@
|
|
| 17 |
"special": true
|
| 18 |
},
|
| 19 |
"2": {
|
| 20 |
-
"content": "
|
| 21 |
"lstrip": false,
|
| 22 |
"normalized": false,
|
| 23 |
"rstrip": false,
|
|
@@ -25,7 +25,7 @@
|
|
| 25 |
"special": true
|
| 26 |
},
|
| 27 |
"3": {
|
| 28 |
-
"content": "
|
| 29 |
"lstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"rstrip": false,
|
|
@@ -33,7 +33,15 @@
|
|
| 33 |
"special": true
|
| 34 |
},
|
| 35 |
"4": {
|
| 36 |
-
"content": "
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
"lstrip": false,
|
| 38 |
"normalized": false,
|
| 39 |
"rstrip": false,
|
|
@@ -44,9 +52,16 @@
|
|
| 44 |
"clean_up_tokenization_spaces": true,
|
| 45 |
"cls_token": "[CLS]",
|
| 46 |
"mask_token": "[MASK]",
|
|
|
|
| 47 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
| 48 |
"pad_token": "[PAD]",
|
|
|
|
|
|
|
| 49 |
"sep_token": "[SEP]",
|
|
|
|
| 50 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
|
|
|
|
|
|
| 51 |
"unk_token": "[UNK]"
|
| 52 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
+
"content": "<bos>",
|
| 5 |
"lstrip": false,
|
| 6 |
"normalized": false,
|
| 7 |
"rstrip": false,
|
|
|
|
| 9 |
"special": true
|
| 10 |
},
|
| 11 |
"1": {
|
| 12 |
+
"content": "<eos>",
|
| 13 |
"lstrip": false,
|
| 14 |
"normalized": false,
|
| 15 |
"rstrip": false,
|
|
|
|
| 17 |
"special": true
|
| 18 |
},
|
| 19 |
"2": {
|
| 20 |
+
"content": "<unk>",
|
| 21 |
"lstrip": false,
|
| 22 |
"normalized": false,
|
| 23 |
"rstrip": false,
|
|
|
|
| 25 |
"special": true
|
| 26 |
},
|
| 27 |
"3": {
|
| 28 |
+
"content": "<pad>",
|
| 29 |
"lstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"rstrip": false,
|
|
|
|
| 33 |
"special": true
|
| 34 |
},
|
| 35 |
"4": {
|
| 36 |
+
"content": "<start_of_turn>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"5": {
|
| 44 |
+
"content": "<end_of_turn>",
|
| 45 |
"lstrip": false,
|
| 46 |
"normalized": false,
|
| 47 |
"rstrip": false,
|
|
|
|
| 52 |
"clean_up_tokenization_spaces": true,
|
| 53 |
"cls_token": "[CLS]",
|
| 54 |
"mask_token": "[MASK]",
|
| 55 |
+
"max_length": 512,
|
| 56 |
"model_max_length": 1000000000000000019884624838656,
|
| 57 |
+
"pad_to_multiple_of": null,
|
| 58 |
"pad_token": "[PAD]",
|
| 59 |
+
"pad_token_type_id": 0,
|
| 60 |
+
"padding_side": "left",
|
| 61 |
"sep_token": "[SEP]",
|
| 62 |
+
"stride": 0,
|
| 63 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 64 |
+
"truncation_side": "right",
|
| 65 |
+
"truncation_strategy": "longest_first",
|
| 66 |
"unk_token": "[UNK]"
|
| 67 |
}
|