anicka commited on
Commit
f9fa62d
·
verified ·
1 Parent(s): 82ccb43

Copy tokenizer_config.json from v1 repo

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +33 -0
tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_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": true,
24
+ "max_length": 4096,
25
+ "model_max_length": 32768,
26
+ "pad_token": "<|endoftext|>",
27
+ "split_special_tokens": false,
28
+ "stride": 0,
29
+ "tokenizer_class": "Qwen2Tokenizer",
30
+ "truncation_side": "right",
31
+ "truncation_strategy": "longest_first",
32
+ "unk_token": null
33
+ }