Upload tokenizer_config.json with huggingface_hub
Browse files- tokenizer_config.json +16 -16
tokenizer_config.json
CHANGED
|
@@ -5,25 +5,25 @@
|
|
| 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": true,
|
| 24 |
"model_max_length": 131072,
|
| 25 |
"pad_token": "<|endoftext|>",
|
| 26 |
"split_special_tokens": false,
|
| 27 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 28 |
"unk_token": null
|
| 29 |
-
}
|
|
|
|
| 5 |
"clean_up_tokenization_spaces": false,
|
| 6 |
"eos_token": "<|im_end|>",
|
| 7 |
"errors": "replace",
|
| 8 |
+
"extra_special_tokens": {
|
| 9 |
+
"<|im_start|>": "<|im_start|>",
|
| 10 |
+
"<|im_end|>": "<|im_end|>",
|
| 11 |
+
"<|object_ref_start|>": "<|object_ref_start|>",
|
| 12 |
+
"<|object_ref_end|>": "<|object_ref_end|>",
|
| 13 |
+
"<|box_start|>": "<|box_start|>",
|
| 14 |
+
"<|box_end|>": "<|box_end|>",
|
| 15 |
+
"<|quad_start|>": "<|quad_start|>",
|
| 16 |
+
"<|quad_end|>": "<|quad_end|>",
|
| 17 |
+
"<|vision_start|>": "<|vision_start|>",
|
| 18 |
+
"<|vision_end|>": "<|vision_end|>",
|
| 19 |
+
"<|vision_pad|>": "<|vision_pad|>",
|
| 20 |
+
"<|image_pad|>": "<|image_pad|>",
|
| 21 |
+
"<|video_pad|>": "<|video_pad|>"
|
| 22 |
+
},
|
| 23 |
"is_local": true,
|
| 24 |
"model_max_length": 131072,
|
| 25 |
"pad_token": "<|endoftext|>",
|
| 26 |
"split_special_tokens": false,
|
| 27 |
"tokenizer_class": "Qwen2Tokenizer",
|
| 28 |
"unk_token": null
|
| 29 |
+
}
|