Upload tokenizer
Browse files- tokenizer_config.json +17 -2
tokenizer_config.json
CHANGED
|
@@ -5,10 +5,25 @@
|
|
| 5 |
"clean_up_tokenization_spaces": false,
|
| 6 |
"eos_token": "<|im_end|>",
|
| 7 |
"errors": "replace",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
"is_local": false,
|
| 9 |
-
"local_files_only": false,
|
| 10 |
"model_max_length": 1010000,
|
| 11 |
-
"
|
|
|
|
| 12 |
"split_special_tokens": false,
|
| 13 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 14 |
"unk_token": null
|
|
|
|
| 5 |
"clean_up_tokenization_spaces": false,
|
| 6 |
"eos_token": "<|im_end|>",
|
| 7 |
"errors": "replace",
|
| 8 |
+
"extra_special_tokens": [
|
| 9 |
+
"<|im_start|>",
|
| 10 |
+
"<|im_end|>",
|
| 11 |
+
"<|object_ref_start|>",
|
| 12 |
+
"<|object_ref_end|>",
|
| 13 |
+
"<|box_start|>",
|
| 14 |
+
"<|box_end|>",
|
| 15 |
+
"<|quad_start|>",
|
| 16 |
+
"<|quad_end|>",
|
| 17 |
+
"<|vision_start|>",
|
| 18 |
+
"<|vision_end|>",
|
| 19 |
+
"<|vision_pad|>",
|
| 20 |
+
"<|image_pad|>",
|
| 21 |
+
"<|video_pad|>"
|
| 22 |
+
],
|
| 23 |
"is_local": false,
|
|
|
|
| 24 |
"model_max_length": 1010000,
|
| 25 |
+
"model_specific_special_tokens": {},
|
| 26 |
+
"pad_token": "<|endoftext|>",
|
| 27 |
"split_special_tokens": false,
|
| 28 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 29 |
"unk_token": null
|