Upload tokenizer
Browse files- tokenizer.json +2 -16
- tokenizer_config.json +0 -7
tokenizer.json
CHANGED
|
@@ -1,21 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
| 5 |
-
"max_length": 256,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
-
"padding": {
|
| 10 |
-
"strategy": {
|
| 11 |
-
"Fixed": 256
|
| 12 |
-
},
|
| 13 |
-
"direction": "Right",
|
| 14 |
-
"pad_to_multiple_of": null,
|
| 15 |
-
"pad_id": 0,
|
| 16 |
-
"pad_type_id": 0,
|
| 17 |
-
"pad_token": "<|endoftext|>"
|
| 18 |
-
},
|
| 19 |
"added_tokens": [
|
| 20 |
{
|
| 21 |
"id": 0,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
tokenizer_config.json
CHANGED
|
@@ -161,16 +161,9 @@
|
|
| 161 |
"clean_up_tokenization_spaces": false,
|
| 162 |
"eos_token": "<|endoftext|>",
|
| 163 |
"extra_special_tokens": {},
|
| 164 |
-
"max_length": 256,
|
| 165 |
"model_max_length": 8192,
|
| 166 |
-
"pad_to_multiple_of": null,
|
| 167 |
"pad_token": "<|endoftext|>",
|
| 168 |
-
"pad_token_type_id": 0,
|
| 169 |
-
"padding_side": "right",
|
| 170 |
-
"stride": 0,
|
| 171 |
"tokenizer_class": "GPT2Tokenizer",
|
| 172 |
-
"truncation_side": "right",
|
| 173 |
-
"truncation_strategy": "longest_first",
|
| 174 |
"unk_token": "<|endoftext|>",
|
| 175 |
"vocab_size": 49152
|
| 176 |
}
|
|
|
|
| 161 |
"clean_up_tokenization_spaces": false,
|
| 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
|
| 169 |
}
|