Upload tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +1 -1
- vocab.json +0 -0
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -9,6 +9,7 @@
|
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false
|
| 11 |
},
|
|
|
|
| 12 |
"cls_token": "<s>",
|
| 13 |
"eos_token": {
|
| 14 |
"__type": "AddedToken",
|
|
@@ -31,7 +32,6 @@
|
|
| 31 |
},
|
| 32 |
"padding_side": "right",
|
| 33 |
"sep_token": "</s>",
|
| 34 |
-
"special_tokens_map_file": "my-gpt2/special_tokens_map.json",
|
| 35 |
"tokenizer_class": "GPT2Tokenizer",
|
| 36 |
"unk_token": {
|
| 37 |
"__type": "AddedToken",
|
|
|
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false
|
| 11 |
},
|
| 12 |
+
"clean_up_tokenization_spaces": true,
|
| 13 |
"cls_token": "<s>",
|
| 14 |
"eos_token": {
|
| 15 |
"__type": "AddedToken",
|
|
|
|
| 32 |
},
|
| 33 |
"padding_side": "right",
|
| 34 |
"sep_token": "</s>",
|
|
|
|
| 35 |
"tokenizer_class": "GPT2Tokenizer",
|
| 36 |
"unk_token": {
|
| 37 |
"__type": "AddedToken",
|
vocab.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|