Upload tokenizer
Browse files- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
special_tokens_map.json
CHANGED
|
@@ -32,6 +32,7 @@
|
|
| 32 |
"rstrip": false,
|
| 33 |
"single_word": false
|
| 34 |
},
|
|
|
|
| 35 |
"unk_token": {
|
| 36 |
"content": "<|endoftext|>",
|
| 37 |
"lstrip": false,
|
|
|
|
| 32 |
"rstrip": false,
|
| 33 |
"single_word": false
|
| 34 |
},
|
| 35 |
+
"pad_token": "<|endoftext|>",
|
| 36 |
"unk_token": {
|
| 37 |
"content": "<|endoftext|>",
|
| 38 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
|
@@ -162,6 +162,7 @@
|
|
| 162 |
"eos_token": "<|endoftext|>",
|
| 163 |
"extra_special_tokens": {},
|
| 164 |
"model_max_length": 8192,
|
|
|
|
| 165 |
"tokenizer_class": "GPT2Tokenizer",
|
| 166 |
"unk_token": "<|endoftext|>",
|
| 167 |
"vocab_size": 49152
|
|
|
|
| 162 |
"eos_token": "<|endoftext|>",
|
| 163 |
"extra_special_tokens": {},
|
| 164 |
"model_max_length": 8192,
|
| 165 |
+
"pad_token": "<|endoftext|>",
|
| 166 |
"tokenizer_class": "GPT2Tokenizer",
|
| 167 |
"unk_token": "<|endoftext|>",
|
| 168 |
"vocab_size": 49152
|