Upload tokenizer
Browse files- tokenizer.json +1 -0
- tokenizer_config.json +2 -1
tokenizer.json
CHANGED
|
@@ -58,6 +58,7 @@
|
|
| 58 |
"end_of_word_suffix": "",
|
| 59 |
"fuse_unk": false,
|
| 60 |
"byte_fallback": false,
|
|
|
|
| 61 |
"vocab": {
|
| 62 |
"!": 0,
|
| 63 |
"\"": 1,
|
|
|
|
| 58 |
"end_of_word_suffix": "",
|
| 59 |
"fuse_unk": false,
|
| 60 |
"byte_fallback": false,
|
| 61 |
+
"ignore_merges": false,
|
| 62 |
"vocab": {
|
| 63 |
"!": 0,
|
| 64 |
"\"": 1,
|
tokenizer_config.json
CHANGED
|
@@ -31,8 +31,9 @@
|
|
| 31 |
"clean_up_tokenization_spaces": true,
|
| 32 |
"eos_token": "#",
|
| 33 |
"errors": "replace",
|
| 34 |
-
"model_max_length":
|
| 35 |
"pad_token": "\"",
|
|
|
|
| 36 |
"tokenizer_class": "GPT2Tokenizer",
|
| 37 |
"unk_token": "<|endoftext|>"
|
| 38 |
}
|
|
|
|
| 31 |
"clean_up_tokenization_spaces": true,
|
| 32 |
"eos_token": "#",
|
| 33 |
"errors": "replace",
|
| 34 |
+
"model_max_length": 2048,
|
| 35 |
"pad_token": "\"",
|
| 36 |
+
"padding_side": "left",
|
| 37 |
"tokenizer_class": "GPT2Tokenizer",
|
| 38 |
"unk_token": "<|endoftext|>"
|
| 39 |
}
|