AlexHT_Hung
commited on
Commit
Β·
a4300b1
1
Parent(s):
29a6e2b
Add <|func_start|> <|func_end|>
Browse files- added_tokens.json +4 -0
- tokenizer.json +19 -1
- tokenizer_config.json +16 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|func_end|>": 35712,
|
| 3 |
+
"<|func_start|>": 35713
|
| 4 |
+
}
|
tokenizer.json
CHANGED
|
@@ -29,6 +29,24 @@
|
|
| 29 |
"rstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
}
|
| 33 |
],
|
| 34 |
"normalizer": {
|
|
@@ -94831,4 +94849,4 @@
|
|
| 94831 |
"β ββββββββββ"
|
| 94832 |
]
|
| 94833 |
}
|
| 94834 |
-
}
|
|
|
|
| 29 |
"rstrip": false,
|
| 30 |
"normalized": false,
|
| 31 |
"special": true
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"id": 35712,
|
| 35 |
+
"content": "<|func_end|>",
|
| 36 |
+
"single_word": true,
|
| 37 |
+
"lstrip": true,
|
| 38 |
+
"rstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"special": false
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"id": 35713,
|
| 44 |
+
"content": "<|func_start|>",
|
| 45 |
+
"single_word": true,
|
| 46 |
+
"lstrip": true,
|
| 47 |
+
"rstrip": true,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"special": false
|
| 50 |
}
|
| 51 |
],
|
| 52 |
"normalizer": {
|
|
|
|
| 94849 |
"β ββββββββββ"
|
| 94850 |
]
|
| 94851 |
}
|
| 94852 |
+
}
|
tokenizer_config.json
CHANGED
|
@@ -25,6 +25,22 @@
|
|
| 25 |
"rstrip": false,
|
| 26 |
"single_word": false,
|
| 27 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
}
|
| 29 |
},
|
| 30 |
"bos_token": "<s>",
|
|
|
|
| 25 |
"rstrip": false,
|
| 26 |
"single_word": false,
|
| 27 |
"special": true
|
| 28 |
+
},
|
| 29 |
+
"35712": {
|
| 30 |
+
"content": "<|func_end|>",
|
| 31 |
+
"lstrip": true,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": true,
|
| 34 |
+
"single_word": true,
|
| 35 |
+
"special": false
|
| 36 |
+
},
|
| 37 |
+
"35713": {
|
| 38 |
+
"content": "<|func_start|>",
|
| 39 |
+
"lstrip": true,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": true,
|
| 42 |
+
"single_word": true,
|
| 43 |
+
"special": false
|
| 44 |
}
|
| 45 |
},
|
| 46 |
"bos_token": "<s>",
|