Commit
•
51b4b9b
1
Parent(s):
0b985ed
Upload tokenizer
Browse files- tokenizer_config.json +1 -1
tokenizer_config.json
CHANGED
|
@@ -9,6 +9,7 @@
|
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false
|
| 11 |
},
|
|
|
|
| 12 |
"eos_token": {
|
| 13 |
"__type": "AddedToken",
|
| 14 |
"content": "<|endoftext|>",
|
|
@@ -20,7 +21,6 @@
|
|
| 20 |
"errors": "replace",
|
| 21 |
"model_max_length": 1000000000000000019884624838656,
|
| 22 |
"pad_token": null,
|
| 23 |
-
"special_tokens_map_file": null,
|
| 24 |
"tokenizer_class": "GPT2Tokenizer",
|
| 25 |
"unk_token": {
|
| 26 |
"__type": "AddedToken",
|
|
|
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false
|
| 11 |
},
|
| 12 |
+
"clean_up_tokenization_spaces": true,
|
| 13 |
"eos_token": {
|
| 14 |
"__type": "AddedToken",
|
| 15 |
"content": "<|endoftext|>",
|
|
|
|
| 21 |
"errors": "replace",
|
| 22 |
"model_max_length": 1000000000000000019884624838656,
|
| 23 |
"pad_token": null,
|
|
|
|
| 24 |
"tokenizer_class": "GPT2Tokenizer",
|
| 25 |
"unk_token": {
|
| 26 |
"__type": "AddedToken",
|