Upload tokenizer
Browse files- tokenizer_config.json +7 -0
tokenizer_config.json
CHANGED
|
@@ -199,9 +199,16 @@
|
|
| 199 |
"clean_up_tokenization_spaces": false,
|
| 200 |
"eos_token": "<|endoftext|>",
|
| 201 |
"errors": "replace",
|
|
|
|
| 202 |
"model_max_length": 131072,
|
|
|
|
| 203 |
"pad_token": "<|endoftext|>",
|
|
|
|
|
|
|
| 204 |
"split_special_tokens": false,
|
|
|
|
| 205 |
"tokenizer_class": "Qwen2Tokenizer",
|
|
|
|
|
|
|
| 206 |
"unk_token": null
|
| 207 |
}
|
|
|
|
| 199 |
"clean_up_tokenization_spaces": false,
|
| 200 |
"eos_token": "<|endoftext|>",
|
| 201 |
"errors": "replace",
|
| 202 |
+
"max_length": 200,
|
| 203 |
"model_max_length": 131072,
|
| 204 |
+
"pad_to_multiple_of": null,
|
| 205 |
"pad_token": "<|endoftext|>",
|
| 206 |
+
"pad_token_type_id": 0,
|
| 207 |
+
"padding_side": "right",
|
| 208 |
"split_special_tokens": false,
|
| 209 |
+
"stride": 0,
|
| 210 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 211 |
+
"truncation_side": "right",
|
| 212 |
+
"truncation_strategy": "longest_first",
|
| 213 |
"unk_token": null
|
| 214 |
}
|