chrisvoncsefalvay
commited on
Commit
•
e7eb7bf
1
Parent(s):
d97b2df
Upload tokenizer
Browse files- added_tokens.json +3 -0
- tokenizer.json +9 -0
- tokenizer_config.json +8 -0
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"Pfizer": 30522
|
3 |
+
}
|
tokenizer.json
CHANGED
@@ -52,6 +52,15 @@
|
|
52 |
"rstrip": false,
|
53 |
"normalized": false,
|
54 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
55 |
}
|
56 |
],
|
57 |
"normalizer": {
|
|
|
52 |
"rstrip": false,
|
53 |
"normalized": false,
|
54 |
"special": true
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"id": 30522,
|
58 |
+
"content": "Pfizer",
|
59 |
+
"single_word": false,
|
60 |
+
"lstrip": false,
|
61 |
+
"rstrip": false,
|
62 |
+
"normalized": true,
|
63 |
+
"special": false
|
64 |
}
|
65 |
],
|
66 |
"normalizer": {
|
tokenizer_config.json
CHANGED
@@ -39,6 +39,14 @@
|
|
39 |
"rstrip": false,
|
40 |
"single_word": false,
|
41 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
42 |
}
|
43 |
},
|
44 |
"clean_up_tokenization_spaces": true,
|
|
|
39 |
"rstrip": false,
|
40 |
"single_word": false,
|
41 |
"special": true
|
42 |
+
},
|
43 |
+
"30522": {
|
44 |
+
"content": "Pfizer",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": true,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": false
|
50 |
}
|
51 |
},
|
52 |
"clean_up_tokenization_spaces": true,
|