Upload tokenizer
Browse files- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +32 -0
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:70d33eab49f262358f962dbf38433dec85c44b71cb05f4b0e23f439c45209218
|
| 3 |
+
size 776904
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -25,6 +25,38 @@
|
|
| 25 |
"single_word": false,
|
| 26 |
"special": true
|
| 27 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
"32000": {
|
| 29 |
"content": "<extra_id_99>",
|
| 30 |
"lstrip": true,
|
|
|
|
| 25 |
"single_word": false,
|
| 26 |
"special": true
|
| 27 |
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": ".",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": false
|
| 35 |
+
},
|
| 36 |
+
"4": {
|
| 37 |
+
"content": "(",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": false
|
| 43 |
+
},
|
| 44 |
+
"5": {
|
| 45 |
+
"content": ")",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": false
|
| 51 |
+
},
|
| 52 |
+
"6": {
|
| 53 |
+
"content": ",-,–,£,€,#,'",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": false
|
| 59 |
+
},
|
| 60 |
"32000": {
|
| 61 |
"content": "<extra_id_99>",
|
| 62 |
"lstrip": true,
|