Upload tokenizer
Browse files- tokenizer_config.json +6 -0
tokenizer_config.json
CHANGED
|
@@ -2062,14 +2062,20 @@
|
|
| 2062 |
"clean_up_tokenization_spaces": true,
|
| 2063 |
"eos_token": "<|eot_id|>",
|
| 2064 |
"extra_special_tokens": {},
|
|
|
|
| 2065 |
"model_input_names": [
|
| 2066 |
"input_ids",
|
| 2067 |
"attention_mask"
|
| 2068 |
],
|
| 2069 |
"model_max_length": 131072,
|
|
|
|
| 2070 |
"pad_token": "<|finetune_right_pad_id|>",
|
|
|
|
| 2071 |
"padding_side": "right",
|
| 2072 |
"processor_class": "MllamaProcessor",
|
|
|
|
| 2073 |
"tokenizer_class": "PreTrainedTokenizer",
|
|
|
|
|
|
|
| 2074 |
"unk_token": null
|
| 2075 |
}
|
|
|
|
| 2062 |
"clean_up_tokenization_spaces": true,
|
| 2063 |
"eos_token": "<|eot_id|>",
|
| 2064 |
"extra_special_tokens": {},
|
| 2065 |
+
"max_length": 2048,
|
| 2066 |
"model_input_names": [
|
| 2067 |
"input_ids",
|
| 2068 |
"attention_mask"
|
| 2069 |
],
|
| 2070 |
"model_max_length": 131072,
|
| 2071 |
+
"pad_to_multiple_of": null,
|
| 2072 |
"pad_token": "<|finetune_right_pad_id|>",
|
| 2073 |
+
"pad_token_type_id": 0,
|
| 2074 |
"padding_side": "right",
|
| 2075 |
"processor_class": "MllamaProcessor",
|
| 2076 |
+
"stride": 0,
|
| 2077 |
"tokenizer_class": "PreTrainedTokenizer",
|
| 2078 |
+
"truncation_side": "right",
|
| 2079 |
+
"truncation_strategy": "longest_first",
|
| 2080 |
"unk_token": null
|
| 2081 |
}
|