Upload tokenizer
Browse files- special_tokens_map.json +1 -0
- tokenizer_config.json +2 -1
special_tokens_map.json
CHANGED
|
@@ -53,6 +53,7 @@
|
|
| 53 |
"rstrip": false,
|
| 54 |
"single_word": false
|
| 55 |
},
|
|
|
|
| 56 |
"unk_token": {
|
| 57 |
"content": "<|endoftext|>",
|
| 58 |
"lstrip": false,
|
|
|
|
| 53 |
"rstrip": false,
|
| 54 |
"single_word": false
|
| 55 |
},
|
| 56 |
+
"pad_token": "<|endoftext|>",
|
| 57 |
"unk_token": {
|
| 58 |
"content": "<|endoftext|>",
|
| 59 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
|
@@ -350,7 +350,8 @@
|
|
| 350 |
"clean_up_tokenization_spaces": true,
|
| 351 |
"eos_token": "<|endoftext|>",
|
| 352 |
"extra_special_tokens": {},
|
| 353 |
-
"model_max_length":
|
|
|
|
| 354 |
"tokenizer_class": "GPT2Tokenizer",
|
| 355 |
"unk_token": "<|endoftext|>",
|
| 356 |
"vocab_size": 49152
|
|
|
|
| 350 |
"clean_up_tokenization_spaces": true,
|
| 351 |
"eos_token": "<|endoftext|>",
|
| 352 |
"extra_special_tokens": {},
|
| 353 |
+
"model_max_length": 2048,
|
| 354 |
+
"pad_token": "<|endoftext|>",
|
| 355 |
"tokenizer_class": "GPT2Tokenizer",
|
| 356 |
"unk_token": "<|endoftext|>",
|
| 357 |
"vocab_size": 49152
|