Upload tokenizer
Browse files- special_tokens_map.json +7 -1
- tokenizer.json +2 -2
special_tokens_map.json
CHANGED
|
@@ -25,7 +25,13 @@
|
|
| 25 |
"rstrip": false,
|
| 26 |
"single_word": false
|
| 27 |
},
|
| 28 |
-
"pad_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
"unk_token": {
|
| 30 |
"content": "<|endoftext|>",
|
| 31 |
"lstrip": false,
|
|
|
|
| 25 |
"rstrip": false,
|
| 26 |
"single_word": false
|
| 27 |
},
|
| 28 |
+
"pad_token": {
|
| 29 |
+
"content": "<|endoftext|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false
|
| 34 |
+
},
|
| 35 |
"unk_token": {
|
| 36 |
"content": "<|endoftext|>",
|
| 37 |
"lstrip": false,
|
tokenizer.json
CHANGED
|
@@ -2,13 +2,13 @@
|
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": {
|
| 4 |
"direction": "Right",
|
| 5 |
-
"max_length":
|
| 6 |
"strategy": "LongestFirst",
|
| 7 |
"stride": 0
|
| 8 |
},
|
| 9 |
"padding": {
|
| 10 |
"strategy": {
|
| 11 |
-
"Fixed":
|
| 12 |
},
|
| 13 |
"direction": "Right",
|
| 14 |
"pad_to_multiple_of": null,
|
|
|
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": {
|
| 4 |
"direction": "Right",
|
| 5 |
+
"max_length": 32,
|
| 6 |
"strategy": "LongestFirst",
|
| 7 |
"stride": 0
|
| 8 |
},
|
| 9 |
"padding": {
|
| 10 |
"strategy": {
|
| 11 |
+
"Fixed": 32
|
| 12 |
},
|
| 13 |
"direction": "Right",
|
| 14 |
"pad_to_multiple_of": null,
|