Commit
•
9883956
1
Parent(s):
10487e9
Upload tokenizer
Browse files- tokenizer_config.json +7 -0
tokenizer_config.json
CHANGED
|
@@ -35,9 +35,16 @@
|
|
| 35 |
"clean_up_tokenization_spaces": false,
|
| 36 |
"eos_token": "<|endoftext|>",
|
| 37 |
"errors": "replace",
|
|
|
|
| 38 |
"model_max_length": 32768,
|
|
|
|
| 39 |
"pad_token": "<|endoftext|>",
|
|
|
|
|
|
|
| 40 |
"split_special_tokens": false,
|
|
|
|
| 41 |
"tokenizer_class": "Qwen2Tokenizer",
|
|
|
|
|
|
|
| 42 |
"unk_token": null
|
| 43 |
}
|
|
|
|
| 35 |
"clean_up_tokenization_spaces": false,
|
| 36 |
"eos_token": "<|endoftext|>",
|
| 37 |
"errors": "replace",
|
| 38 |
+
"max_length": 512,
|
| 39 |
"model_max_length": 32768,
|
| 40 |
+
"pad_to_multiple_of": null,
|
| 41 |
"pad_token": "<|endoftext|>",
|
| 42 |
+
"pad_token_type_id": 0,
|
| 43 |
+
"padding_side": "right",
|
| 44 |
"split_special_tokens": false,
|
| 45 |
+
"stride": 0,
|
| 46 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 47 |
+
"truncation_side": "right",
|
| 48 |
+
"truncation_strategy": "longest_first",
|
| 49 |
"unk_token": null
|
| 50 |
}
|