Upload tokenizer
Browse files- special_tokens_map.json +7 -0
- tokenizer_config.json +1 -0
special_tokens_map.json
CHANGED
@@ -13,6 +13,13 @@
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
"unk_token": {
|
17 |
"content": "<|endoftext|>",
|
18 |
"lstrip": false,
|
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|pad|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
"unk_token": {
|
24 |
"content": "<|endoftext|>",
|
25 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
@@ -183,6 +183,7 @@
|
|
183 |
"clean_up_tokenization_spaces": false,
|
184 |
"eos_token": "<|endoftext|>",
|
185 |
"model_max_length": 8192,
|
|
|
186 |
"tokenizer_class": "GPT2Tokenizer",
|
187 |
"unk_token": "<|endoftext|>"
|
188 |
}
|
|
|
183 |
"clean_up_tokenization_spaces": false,
|
184 |
"eos_token": "<|endoftext|>",
|
185 |
"model_max_length": 8192,
|
186 |
+
"pad_token": "<|pad|>",
|
187 |
"tokenizer_class": "GPT2Tokenizer",
|
188 |
"unk_token": "<|endoftext|>"
|
189 |
}
|