Upload tokenizer
Browse files- tokenizer_config.json +5 -1
tokenizer_config.json
CHANGED
|
@@ -2052,10 +2052,14 @@
|
|
| 2052 |
"bos_token": "<|begin_of_text|>",
|
| 2053 |
"clean_up_tokenization_spaces": true,
|
| 2054 |
"eos_token": "<|end_of_text|>",
|
|
|
|
| 2055 |
"model_input_names": [
|
| 2056 |
"input_ids",
|
| 2057 |
"attention_mask"
|
| 2058 |
],
|
| 2059 |
"model_max_length": 131072,
|
| 2060 |
-
"
|
|
|
|
|
|
|
|
|
|
| 2061 |
}
|
|
|
|
| 2052 |
"bos_token": "<|begin_of_text|>",
|
| 2053 |
"clean_up_tokenization_spaces": true,
|
| 2054 |
"eos_token": "<|end_of_text|>",
|
| 2055 |
+
"max_length": 100,
|
| 2056 |
"model_input_names": [
|
| 2057 |
"input_ids",
|
| 2058 |
"attention_mask"
|
| 2059 |
],
|
| 2060 |
"model_max_length": 131072,
|
| 2061 |
+
"stride": 0,
|
| 2062 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 2063 |
+
"truncation_side": "right",
|
| 2064 |
+
"truncation_strategy": "longest_first"
|
| 2065 |
}
|