Upload tokenizer
Browse files- tokenizer_config.json +4 -0
tokenizer_config.json
CHANGED
@@ -2054,11 +2054,15 @@
|
|
2054 |
"clean_up_tokenization_spaces": true,
|
2055 |
"eos_token": "<|eot_id|>",
|
2056 |
"extra_special_tokens": {},
|
|
|
2057 |
"model_input_names": [
|
2058 |
"input_ids",
|
2059 |
"attention_mask"
|
2060 |
],
|
2061 |
"model_max_length": 131072,
|
|
|
2062 |
"pad_token": "<|eot_id|>",
|
|
|
|
|
2063 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
2064 |
}
|
|
|
2054 |
"clean_up_tokenization_spaces": true,
|
2055 |
"eos_token": "<|eot_id|>",
|
2056 |
"extra_special_tokens": {},
|
2057 |
+
"max_length": 512,
|
2058 |
"model_input_names": [
|
2059 |
"input_ids",
|
2060 |
"attention_mask"
|
2061 |
],
|
2062 |
"model_max_length": 131072,
|
2063 |
+
"pad_to_multiple_of": null,
|
2064 |
"pad_token": "<|eot_id|>",
|
2065 |
+
"pad_token_type_id": 0,
|
2066 |
+
"padding_side": "right",
|
2067 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
2068 |
}
|