Commit
·
5ec4aaa
1
Parent(s):
a9bb02f
Fixed tokenizer
Browse files- tokenizer.json +54 -0
- tokenizer_config.json +48 -0
tokenizer.json
CHANGED
|
@@ -29,6 +29,60 @@
|
|
| 29 |
"rstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
}
|
| 33 |
],
|
| 34 |
"normalizer": {
|
|
|
|
| 29 |
"rstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"special": true
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"id": 3,
|
| 35 |
+
"content": "[INST]",
|
| 36 |
+
"single_word": false,
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"special": false
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"id": 4,
|
| 44 |
+
"content": "[/INST]",
|
| 45 |
+
"single_word": false,
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"normalized": true,
|
| 49 |
+
"special": false
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"id": 10,
|
| 53 |
+
"content": "[IMG]",
|
| 54 |
+
"single_word": false,
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"normalized": true,
|
| 58 |
+
"special": false
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"id": 11,
|
| 62 |
+
"content": "[PREFIX]",
|
| 63 |
+
"single_word": false,
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"normalized": true,
|
| 67 |
+
"special": false
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"id": 12,
|
| 71 |
+
"content": "[MIDDLE]",
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"lstrip": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"normalized": true,
|
| 76 |
+
"special": false
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"id": 13,
|
| 80 |
+
"content": "[SUFFIX]",
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"lstrip": false,
|
| 83 |
+
"rstrip": false,
|
| 84 |
+
"normalized": true,
|
| 85 |
+
"special": false
|
| 86 |
}
|
| 87 |
],
|
| 88 |
"normalizer": {
|
tokenizer_config.json
CHANGED
|
@@ -26,6 +26,54 @@
|
|
| 26 |
"rstrip": false,
|
| 27 |
"single_word": false,
|
| 28 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
}
|
| 30 |
},
|
| 31 |
"bos_token": "<s>",
|
|
|
|
| 26 |
"rstrip": false,
|
| 27 |
"single_word": false,
|
| 28 |
"special": true
|
| 29 |
+
},
|
| 30 |
+
"3": {
|
| 31 |
+
"content": "[INST]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": false
|
| 37 |
+
},
|
| 38 |
+
"4": {
|
| 39 |
+
"content": "[/INST]",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": true,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"10": {
|
| 47 |
+
"content": "[IMG]",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": true,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"11": {
|
| 55 |
+
"content": "[PREFIX]",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": true,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"12": {
|
| 63 |
+
"content": "[MIDDLE]",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": true,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": false
|
| 69 |
+
},
|
| 70 |
+
"13": {
|
| 71 |
+
"content": "[SUFFIX]",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": true,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": false
|
| 77 |
}
|
| 78 |
},
|
| 79 |
"bos_token": "<s>",
|