Upload tokenizer
Browse files- tokenizer_config.json +5 -1
tokenizer_config.json
CHANGED
@@ -2055,6 +2055,7 @@
|
|
2055 |
"clean_up_tokenization_spaces": true,
|
2056 |
"eos_token": "<|eot_id|>",
|
2057 |
"extra_special_tokens": {},
|
|
|
2058 |
"model_input_names": [
|
2059 |
"input_ids",
|
2060 |
"attention_mask"
|
@@ -2062,5 +2063,8 @@
|
|
2062 |
"model_max_length": 4096,
|
2063 |
"pad_token": "<|eot_id|>",
|
2064 |
"padding_side": "left",
|
2065 |
-
"
|
|
|
|
|
|
|
2066 |
}
|
|
|
2055 |
"clean_up_tokenization_spaces": true,
|
2056 |
"eos_token": "<|eot_id|>",
|
2057 |
"extra_special_tokens": {},
|
2058 |
+
"max_length": 4096,
|
2059 |
"model_input_names": [
|
2060 |
"input_ids",
|
2061 |
"attention_mask"
|
|
|
2063 |
"model_max_length": 4096,
|
2064 |
"pad_token": "<|eot_id|>",
|
2065 |
"padding_side": "left",
|
2066 |
+
"stride": 0,
|
2067 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
2068 |
+
"truncation_side": "right",
|
2069 |
+
"truncation_strategy": "longest_first"
|
2070 |
}
|