Thirawarit commited on
Commit
3482901
1 Parent(s): 99503bb

Upload processor

Browse files
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
merges.txt CHANGED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -1,29 +1,19 @@
1
  {
2
- "bos_token": {
3
- "content": "</s>",
4
- "lstrip": false,
5
- "normalized": true,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
  "eos_token": {
10
- "content": "</s>",
11
  "lstrip": false,
12
- "normalized": true,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
  "pad_token": {
17
- "content": "<pad>",
18
- "lstrip": false,
19
- "normalized": true,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
- "unk_token": {
24
- "content": "</s>",
25
  "lstrip": false,
26
- "normalized": true,
27
  "rstrip": false,
28
  "single_word": false
29
  }
 
1
  {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
 
 
 
6
  "eos_token": {
7
+ "content": "<|endoftext|>",
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
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,31 +1,44 @@
1
  {
2
- "add_bos_token": true,
3
  "add_prefix_space": false,
4
  "added_tokens_decoder": {
5
- "1": {
6
- "content": "<pad>",
7
  "lstrip": false,
8
- "normalized": true,
9
  "rstrip": false,
10
  "single_word": false,
11
  "special": true
12
  },
13
- "2": {
14
- "content": "</s>",
15
  "lstrip": false,
16
- "normalized": true,
 
 
 
 
 
 
 
 
17
  "rstrip": false,
18
  "single_word": false,
19
  "special": true
20
  }
21
  },
22
- "bos_token": "</s>",
23
- "clean_up_tokenization_spaces": true,
24
- "eos_token": "</s>",
 
 
 
 
 
25
  "errors": "replace",
26
- "model_max_length": 1000000000000000019884624838656,
27
- "pad_token": "<pad>",
28
  "processor_class": "Blip2Processor",
29
- "tokenizer_class": "GPT2Tokenizer",
30
- "unk_token": "</s>"
 
31
  }
 
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
  },
29
+ "additional_special_tokens": [
30
+ "<|im_start|>",
31
+ "<|im_end|>"
32
+ ],
33
+ "bos_token": null,
34
+ "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 %}",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "<|endoftext|>",
37
  "errors": "replace",
38
+ "model_max_length": 32768,
39
+ "pad_token": "<|endoftext|>",
40
  "processor_class": "Blip2Processor",
41
+ "split_special_tokens": false,
42
+ "tokenizer_class": "Qwen2Tokenizer",
43
+ "unk_token": null
44
  }
vocab.json CHANGED
The diff for this file is too large to render. See raw diff