Hugging Face's logo

lmms-lab
/
llavanext-qwen-siglip-tokenizer

Text Generation
Transformers
llava
conversational
Inference Endpoints
Model card Files Community
kcz358 commited on
Commit
0c92b7b
·
verified ·
1 Parent(s): fab3207

Upload tokenizer

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +10 -13
  2. tokenizer_config.json +39 -20
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_config.json CHANGED
@@ -1,33 +1,52 @@
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
- "unk_token": "<unk>"
 
 
 
 
 
33
  }
 
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": false,
32
+ "rstrip": false,
33
  "single_word": false,
34
  "special": true
35
  }
36
  },
37
+ "additional_special_tokens": [
38
+ "<|im_start|>",
39
+ "<|im_end|>"
 
 
 
40
  ],
41
+ "bos_token": null,
42
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
43
+ "clean_up_tokenization_spaces": false,
44
+ "eos_token": "<|im_end|>",
45
+ "errors": "replace",
46
+ "model_max_length": 32768,
47
+ "pad_token": "<|endoftext|>",
48
+ "padding_side": "right",
49
+ "split_special_tokens": false,
50
+ "tokenizer_class": "Qwen2Tokenizer",
51
+ "unk_token": null
52
  }