Upload tokenizer
Browse files- special_tokens_map.json +1 -7
- tokenizer_config.json +1 -5
special_tokens_map.json
CHANGED
@@ -19,11 +19,5 @@
|
|
19 |
"rstrip": false,
|
20 |
"single_word": false
|
21 |
},
|
22 |
-
"pad_token":
|
23 |
-
"content": "<|endoftext|>",
|
24 |
-
"lstrip": false,
|
25 |
-
"normalized": false,
|
26 |
-
"rstrip": false,
|
27 |
-
"single_word": false
|
28 |
-
}
|
29 |
}
|
|
|
19 |
"rstrip": false,
|
20 |
"single_word": false
|
21 |
},
|
22 |
+
"pad_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
}
|
tokenizer_config.json
CHANGED
@@ -113,11 +113,7 @@
|
|
113 |
],
|
114 |
"clean_up_tokenization_spaces": true,
|
115 |
"eos_token": "<|endoftext|>",
|
116 |
-
"max_length": 2048,
|
117 |
"model_max_length": 2048,
|
118 |
"pad_token": "<|endoftext|>",
|
119 |
-
"
|
120 |
-
"tokenizer_class": "PreTrainedTokenizerFast",
|
121 |
-
"truncation_side": "right",
|
122 |
-
"truncation_strategy": "longest_first"
|
123 |
}
|
|
|
113 |
],
|
114 |
"clean_up_tokenization_spaces": true,
|
115 |
"eos_token": "<|endoftext|>",
|
|
|
116 |
"model_max_length": 2048,
|
117 |
"pad_token": "<|endoftext|>",
|
118 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
|
|
|
|
|
|
119 |
}
|