Upload tokenizer
Browse files- special_tokens_map.json +1 -1
- tokenizer.json +0 -0
- tokenizer_config.json +25 -1
special_tokens_map.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token": "[
|
| 3 |
"cls_token": "[CLS]",
|
| 4 |
"eos_token": "[EOS]",
|
| 5 |
"mask_token": "[MASK]",
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": "[BOS]",
|
| 3 |
"cls_token": "[CLS]",
|
| 4 |
"eos_token": "[EOS]",
|
| 5 |
"mask_token": "[MASK]",
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -41,15 +41,39 @@
|
|
| 41 |
"special": true
|
| 42 |
},
|
| 43 |
"5": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
"content": "[EOS]",
|
| 45 |
"lstrip": false,
|
| 46 |
"normalized": false,
|
| 47 |
"rstrip": false,
|
| 48 |
"single_word": false,
|
| 49 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
}
|
| 51 |
},
|
| 52 |
-
"bos_token": "[
|
| 53 |
"clean_up_tokenization_spaces": false,
|
| 54 |
"cls_token": "[CLS]",
|
| 55 |
"eos_token": "[EOS]",
|
|
|
|
| 41 |
"special": true
|
| 42 |
},
|
| 43 |
"5": {
|
| 44 |
+
"content": "[BOS]",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"6": {
|
| 52 |
"content": "[EOS]",
|
| 53 |
"lstrip": false,
|
| 54 |
"normalized": false,
|
| 55 |
"rstrip": false,
|
| 56 |
"single_word": false,
|
| 57 |
"special": true
|
| 58 |
+
},
|
| 59 |
+
"7": {
|
| 60 |
+
"content": "[PROMPT]",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"8": {
|
| 68 |
+
"content": "[TIMESTAMP]",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
}
|
| 75 |
},
|
| 76 |
+
"bos_token": "[BOS]",
|
| 77 |
"clean_up_tokenization_spaces": false,
|
| 78 |
"cls_token": "[CLS]",
|
| 79 |
"eos_token": "[EOS]",
|