Fix Tokenizer bug on transfomers>4.34
Browse files- added_tokens.json +0 -0
- tokenizer.json +0 -0
- tokenizer_config.json +8 -1
added_tokens.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -18,7 +18,14 @@
|
|
| 18 |
},
|
| 19 |
"legacy": false,
|
| 20 |
"model_max_length": 1000000000000000019884624838656,
|
| 21 |
-
"pad_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
"sp_model_kwargs": {},
|
| 23 |
"tokenizer_class": "LlamaTokenizer",
|
| 24 |
"unk_token": {
|
|
|
|
| 18 |
},
|
| 19 |
"legacy": false,
|
| 20 |
"model_max_length": 1000000000000000019884624838656,
|
| 21 |
+
"pad_token": {
|
| 22 |
+
"__type": "AddedToken",
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false
|
| 28 |
+
},
|
| 29 |
"sp_model_kwargs": {},
|
| 30 |
"tokenizer_class": "LlamaTokenizer",
|
| 31 |
"unk_token": {
|