Hugging Face's logo

HuggingFaceM4
/
tiny-random-idefics

Transformers
PyTorch
idefics
pretraining
text-generation-inference
Inference Endpoints
Model card Files Community
5
Leyo commited on
Commit
b08e9ee
•
1 Parent(s): a3b6c1d

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +0 -1
  2. special_tokens_map.json +12 -18
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +51 -27
added_tokens.json CHANGED
@@ -1,4 +1,3 @@
1
  {
2
- "<fake_token_around_image>": 32000,
3
  "<image>": 32001
4
  }
 
1
  {
 
2
  "<image>": 32001
3
  }
special_tokens_map.json CHANGED
@@ -1,39 +1,33 @@
1
  {
2
  "additional_special_tokens": [
3
- {
4
- "content": "<fake_token_around_image>",
5
- "lstrip": false,
6
- "normalized": true,
7
- "rstrip": false,
8
- "single_word": false
9
- },
10
- {
11
- "content": "<image>",
12
- "lstrip": false,
13
- "normalized": true,
14
- "rstrip": false,
15
- "single_word": false
16
- }
17
  ],
18
  "bos_token": {
19
  "content": "<s>",
20
  "lstrip": false,
21
- "normalized": true,
22
  "rstrip": false,
23
  "single_word": false
24
  },
25
  "eos_token": {
26
  "content": "</s>",
27
  "lstrip": false,
28
- "normalized": true,
 
 
 
 
 
 
 
29
  "rstrip": false,
30
  "single_word": false
31
  },
32
- "pad_token": "<unk>",
33
  "unk_token": {
34
  "content": "<unk>",
35
  "lstrip": false,
36
- "normalized": true,
37
  "rstrip": false,
38
  "single_word": false
39
  }
 
1
  {
2
  "additional_special_tokens": [
3
+ "<fake_token_around_image>",
4
+ "<image>"
 
 
 
 
 
 
 
 
 
 
 
 
5
  ],
6
  "bos_token": {
7
  "content": "<s>",
8
  "lstrip": false,
9
+ "normalized": false,
10
  "rstrip": false,
11
  "single_word": false
12
  },
13
  "eos_token": {
14
  "content": "</s>",
15
  "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
  "rstrip": false,
25
  "single_word": false
26
  },
 
27
  "unk_token": {
28
  "content": "<unk>",
29
  "lstrip": false,
30
+ "normalized": false,
31
  "rstrip": false,
32
  "single_word": false
33
  }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,35 +1,59 @@
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": true,
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": true,
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": true,
32
- "rstrip": false,
33
- "single_word": false
34
- }
35
  }
 
1
  {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "32000": {
28
+ "content": "<fake_token_around_image>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "32001": {
36
+ "content": "<image>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
  },
44
+ "additional_special_tokens": [
45
+ "<fake_token_around_image>",
46
+ "<image>"
47
+ ],
48
+ "bos_token": "<s>",
49
  "clean_up_tokenization_spaces": false,
50
+ "eos_token": "</s>",
 
 
 
 
 
 
 
51
  "legacy": true,
52
  "model_max_length": 2048,
53
+ "pad_token": "<unk>",
54
  "sp_model_kwargs": {},
55
+ "spaces_between_special_tokens": false,
56
  "tokenizer_class": "LlamaTokenizer",
57
+ "unk_token": "<unk>",
58
+ "use_default_system_prompt": true
 
 
 
 
 
 
59
  }