Leyo commited on
Commit
29a2b65
1 Parent(s): 5a06c17

Upload tokenizer

Browse files
added_tokens.json CHANGED
@@ -1,5 +1,8 @@
1
  {
 
2
  "<end_of_utterance>": 32002,
3
  "<fake_token_around_image>": 32000,
4
- "<image>": 32001
 
 
5
  }
 
1
  {
2
+ "</s>": 2,
3
  "<end_of_utterance>": 32002,
4
  "<fake_token_around_image>": 32000,
5
+ "<image>": 32001,
6
+ "<s>": 1,
7
+ "<unk>": 0
8
  }
special_tokens_map.json CHANGED
@@ -1,47 +1,11 @@
1
  {
2
  "additional_special_tokens": [
3
- {
4
- "content": "<fake_token_around_image>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false
9
- },
10
- {
11
- "content": "<image>",
12
- "lstrip": false,
13
- "normalized": false,
14
- "rstrip": false,
15
- "single_word": false
16
- },
17
- {
18
- "content": "<end_of_utterance>",
19
- "lstrip": false,
20
- "normalized": false,
21
- "rstrip": false,
22
- "single_word": false
23
- }
24
  ],
25
- "bos_token": {
26
- "content": "<s>",
27
- "lstrip": false,
28
- "normalized": false,
29
- "rstrip": false,
30
- "single_word": false
31
- },
32
- "eos_token": {
33
- "content": "</s>",
34
- "lstrip": false,
35
- "normalized": false,
36
- "rstrip": false,
37
- "single_word": false
38
- },
39
  "pad_token": "<unk>",
40
- "unk_token": {
41
- "content": "<unk>",
42
- "lstrip": false,
43
- "normalized": false,
44
- "rstrip": false,
45
- "single_word": false
46
- }
47
  }
 
1
  {
2
  "additional_special_tokens": [
3
+ "<fake_token_around_image>",
4
+ "<image>",
5
+ "<end_of_utterance>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  ],
7
+ "bos_token": "<s>",
8
+ "eos_token": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
9
  "pad_token": "<unk>",
10
+ "unk_token": "<unk>"
 
 
 
 
 
 
11
  }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,35 +1,70 @@
1
  {
2
  "add_bos_token": true,
3
  "add_eos_token": false,
4
- "bos_token": {
5
- "__type": "AddedToken",
6
- "content": "<s>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  },
 
 
 
 
 
 
12
  "clean_up_tokenization_spaces": false,
13
- "eos_token": {
14
- "__type": "AddedToken",
15
- "content": "</s>",
16
- "lstrip": false,
17
- "normalized": false,
18
- "rstrip": false,
19
- "single_word": false
20
- },
21
  "legacy": true,
22
  "model_max_length": 2048,
23
- "pad_token": null,
24
  "sp_model_kwargs": {},
25
- "special_tokens_map_file": "/Users/leotronchon/.cache/huggingface/hub/models--huggyllama--llama-7b/snapshots/8416d3fefb0cb3ff5775a7b13c1692d10ff1aa16/special_tokens_map.json",
26
  "tokenizer_class": "LlamaTokenizer",
27
- "unk_token": {
28
- "__type": "AddedToken",
29
- "content": "<unk>",
30
- "lstrip": false,
31
- "normalized": false,
32
- "rstrip": false,
33
- "single_word": false
34
- }
35
  }
 
1
  {
2
  "add_bos_token": true,
3
  "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "<fake_token_around_image>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<image>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32002": {
46
+ "content": "<end_of_utterance>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ }
53
  },
54
+ "additional_special_tokens": [
55
+ "<fake_token_around_image>",
56
+ "<image>",
57
+ "<end_of_utterance>"
58
+ ],
59
+ "bos_token": "<s>",
60
  "clean_up_tokenization_spaces": false,
61
+ "eos_token": "</s>",
 
 
 
 
 
 
 
62
  "legacy": true,
63
  "model_max_length": 2048,
64
+ "pad_token": "<unk>",
65
  "sp_model_kwargs": {},
66
+ "spaces_between_special_tokens": false,
67
  "tokenizer_class": "LlamaTokenizer",
68
+ "unk_token": "<unk>",
69
+ "use_default_system_prompt": true
 
 
 
 
 
 
70
  }