Upload tokenizer
Browse files- tokenizer.json +1 -1
- tokenizer_config.json +1 -5
tokenizer.json
CHANGED
@@ -2,7 +2,7 @@
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
-
"max_length":
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
+
"max_length": 1024,
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
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 |
}
|