Upload tokenizer
Browse files- tokenizer.json +2 -2
- tokenizer_config.json +7 -0
tokenizer.json
CHANGED
|
@@ -2,13 +2,13 @@
|
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": {
|
| 4 |
"direction": "Right",
|
| 5 |
-
"max_length":
|
| 6 |
"strategy": "LongestFirst",
|
| 7 |
"stride": 0
|
| 8 |
},
|
| 9 |
"padding": {
|
| 10 |
"strategy": {
|
| 11 |
-
"Fixed":
|
| 12 |
},
|
| 13 |
"direction": "Right",
|
| 14 |
"pad_to_multiple_of": null,
|
|
|
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": {
|
| 4 |
"direction": "Right",
|
| 5 |
+
"max_length": 128,
|
| 6 |
"strategy": "LongestFirst",
|
| 7 |
"stride": 0
|
| 8 |
},
|
| 9 |
"padding": {
|
| 10 |
"strategy": {
|
| 11 |
+
"Fixed": 128
|
| 12 |
},
|
| 13 |
"direction": "Right",
|
| 14 |
"pad_to_multiple_of": null,
|
tokenizer_config.json
CHANGED
|
@@ -23,8 +23,15 @@
|
|
| 23 |
"clean_up_tokenization_spaces": false,
|
| 24 |
"eos_token": "<|endoftext|>",
|
| 25 |
"errors": "replace",
|
|
|
|
| 26 |
"model_max_length": 1024,
|
|
|
|
| 27 |
"pad_token": "[PAD]",
|
|
|
|
|
|
|
|
|
|
| 28 |
"tokenizer_class": "GPT2Tokenizer",
|
|
|
|
|
|
|
| 29 |
"unk_token": "<|endoftext|>"
|
| 30 |
}
|
|
|
|
| 23 |
"clean_up_tokenization_spaces": false,
|
| 24 |
"eos_token": "<|endoftext|>",
|
| 25 |
"errors": "replace",
|
| 26 |
+
"max_length": 512,
|
| 27 |
"model_max_length": 1024,
|
| 28 |
+
"pad_to_multiple_of": null,
|
| 29 |
"pad_token": "[PAD]",
|
| 30 |
+
"pad_token_type_id": 0,
|
| 31 |
+
"padding_side": "right",
|
| 32 |
+
"stride": 0,
|
| 33 |
"tokenizer_class": "GPT2Tokenizer",
|
| 34 |
+
"truncation_side": "right",
|
| 35 |
+
"truncation_strategy": "longest_first",
|
| 36 |
"unk_token": "<|endoftext|>"
|
| 37 |
}
|