Efi commited on
Upload tokenizer
Browse files- special_tokens_map.json +3 -14
- tokenizer_config.json +4 -3
special_tokens_map.json
CHANGED
|
@@ -1,18 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token":
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
"normalized": false,
|
| 6 |
-
"rstrip": false,
|
| 7 |
-
"single_word": false
|
| 8 |
-
},
|
| 9 |
-
"eos_token": {
|
| 10 |
-
"content": "<|endoftext|>",
|
| 11 |
-
"lstrip": false,
|
| 12 |
-
"normalized": false,
|
| 13 |
-
"rstrip": false,
|
| 14 |
-
"single_word": false
|
| 15 |
-
},
|
| 16 |
"unk_token": {
|
| 17 |
"content": "<|endoftext|>",
|
| 18 |
"lstrip": false,
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"pad_token": "<pad>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"unk_token": {
|
| 6 |
"content": "<|endoftext|>",
|
| 7 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
|
@@ -34,10 +34,11 @@
|
|
| 34 |
"special": true
|
| 35 |
}
|
| 36 |
},
|
| 37 |
-
"bos_token": "<
|
| 38 |
"clean_up_tokenization_spaces": false,
|
| 39 |
-
"eos_token": "<
|
| 40 |
-
"model_max_length":
|
|
|
|
| 41 |
"tokenizer_class": "GPT2Tokenizer",
|
| 42 |
"unk_token": "<|endoftext|>"
|
| 43 |
}
|
|
|
|
| 34 |
"special": true
|
| 35 |
}
|
| 36 |
},
|
| 37 |
+
"bos_token": "<s>",
|
| 38 |
"clean_up_tokenization_spaces": false,
|
| 39 |
+
"eos_token": "</s>",
|
| 40 |
+
"model_max_length": 128,
|
| 41 |
+
"pad_token": "<pad>",
|
| 42 |
"tokenizer_class": "GPT2Tokenizer",
|
| 43 |
"unk_token": "<|endoftext|>"
|
| 44 |
}
|