huseinzol05 commited on
Commit
eb43586
1 Parent(s): 148de78

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</audio>": 151649,
3
+ "</image>": 151647,
4
+ "<audio>": 151648,
5
+ "<image>": 151646,
6
+ "<|endoftext|>": 151643,
7
+ "<|im_end|>": 151645,
8
+ "<|im_start|>": 151644
9
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -1,23 +1,20 @@
1
  {
 
 
 
 
2
  "eos_token": {
3
- "content": "</s>",
4
- "lstrip": true,
5
  "normalized": false,
6
- "rstrip": true,
7
  "single_word": false
8
  },
9
  "pad_token": {
10
- "content": "</s>",
11
- "lstrip": true,
12
  "normalized": false,
13
- "rstrip": true,
14
- "single_word": false
15
- },
16
- "unk_token": {
17
- "content": "<unk>",
18
- "lstrip": true,
19
- "normalized": false,
20
- "rstrip": true,
21
  "single_word": false
22
  }
23
  }
 
1
  {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
  "eos_token": {
7
+ "content": "<|im_end|>",
8
+ "lstrip": false,
9
  "normalized": false,
10
+ "rstrip": false,
11
  "single_word": false
12
  },
13
  "pad_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
  "normalized": false,
17
+ "rstrip": false,
 
 
 
 
 
 
 
18
  "single_word": false
19
  }
20
  }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,34 +1,79 @@
1
  {
 
2
  "added_tokens_decoder": {
3
- "1": {
4
- "content": "</s>",
5
- "lstrip": true,
6
  "normalized": false,
7
- "rstrip": true,
8
  "single_word": false,
9
  "special": true
10
  },
11
- "2": {
12
- "content": "<unk>",
13
- "lstrip": true,
14
  "normalized": false,
15
- "rstrip": true,
16
  "single_word": false,
17
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
18
  }
19
  },
20
- "additional_special_tokens": [],
21
- "clean_up_tokenization_spaces": true,
22
- "do_lower_case": true,
23
- "eos_token": "</s>",
24
- "model_input_names": [
25
- "input_ids"
26
  ],
27
- "model_max_length": 64,
28
- "pad_token": "</s>",
29
- "processor_class": "SiglipProcessor",
30
- "sp_model_kwargs": {},
31
- "tokenizer_class": "SiglipTokenizer",
32
- "trust_remote_code": false,
33
- "unk_token": "<unk>"
 
 
 
 
 
 
 
34
  }
 
1
  {
2
+ "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
  "normalized": false,
8
+ "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
  },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
  "normalized": false,
16
+ "rstrip": false,
17
  "single_word": false,
18
  "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<image>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "151647": {
37
+ "content": "</image>",
38
+ "lstrip": false,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "151648": {
45
+ "content": "<audio>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "151649": {
53
+ "content": "</audio>",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
  }
60
  },
61
+ "additional_special_tokens": [
62
+ "<|im_start|>",
63
+ "<|im_end|>"
 
 
 
64
  ],
65
+ "bos_token": null,
66
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
67
+ "clean_up_tokenization_spaces": false,
68
+ "eos_token": "<|im_end|>",
69
+ "errors": "replace",
70
+ "max_length": 2048,
71
+ "model_max_length": 32768,
72
+ "pad_token": "<|endoftext|>",
73
+ "split_special_tokens": false,
74
+ "stride": 0,
75
+ "tokenizer_class": "Qwen2Tokenizer",
76
+ "truncation_side": "right",
77
+ "truncation_strategy": "longest_first",
78
+ "unk_token": null
79
  }
vocab.json ADDED
The diff for this file is too large to render. See raw diff