Commit
•
b31e2f0
1
Parent(s):
9249694
Upload tokenizer
Browse files- special_tokens_map.json +2 -2
- tokenizer.json +2 -11
- tokenizer_config.json +0 -0
special_tokens_map.json
CHANGED
|
@@ -7,14 +7,14 @@
|
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
-
"content": "
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"pad_token": {
|
| 17 |
-
"content": "
|
| 18 |
"lstrip": false,
|
| 19 |
"normalized": false,
|
| 20 |
"rstrip": false,
|
|
|
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"pad_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
"lstrip": false,
|
| 19 |
"normalized": false,
|
| 20 |
"rstrip": false,
|
tokenizer.json
CHANGED
|
@@ -23,21 +23,12 @@
|
|
| 23 |
},
|
| 24 |
{
|
| 25 |
"id": 2,
|
| 26 |
-
"content": "
|
| 27 |
"single_word": false,
|
| 28 |
"lstrip": false,
|
| 29 |
"rstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"special": true
|
| 32 |
-
},
|
| 33 |
-
{
|
| 34 |
-
"id": 32000,
|
| 35 |
-
"content": "<|im_start|>",
|
| 36 |
-
"single_word": false,
|
| 37 |
-
"lstrip": false,
|
| 38 |
-
"rstrip": false,
|
| 39 |
-
"normalized": false,
|
| 40 |
-
"special": false
|
| 41 |
}
|
| 42 |
],
|
| 43 |
"normalizer": {
|
|
@@ -146,7 +137,7 @@
|
|
| 146 |
"vocab": {
|
| 147 |
"<unk>": 0,
|
| 148 |
"<s>": 1,
|
| 149 |
-
"
|
| 150 |
"<0x00>": 3,
|
| 151 |
"<0x01>": 4,
|
| 152 |
"<0x02>": 5,
|
|
|
|
| 23 |
},
|
| 24 |
{
|
| 25 |
"id": 2,
|
| 26 |
+
"content": "</s>",
|
| 27 |
"single_word": false,
|
| 28 |
"lstrip": false,
|
| 29 |
"rstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
}
|
| 33 |
],
|
| 34 |
"normalizer": {
|
|
|
|
| 137 |
"vocab": {
|
| 138 |
"<unk>": 0,
|
| 139 |
"<s>": 1,
|
| 140 |
+
"</s>": 2,
|
| 141 |
"<0x00>": 3,
|
| 142 |
"<0x01>": 4,
|
| 143 |
"<0x02>": 5,
|
tokenizer_config.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|