Hugging Face's logo

crscardellino
/
flisol-cba-martin-fierro

Text Generation
Transformers
PyTorch
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files
crscardellino commited on
Commit
92f59d3
•
1 Parent(s): 48a9e41

Upload tokenizer

Browse files
Files changed (4) hide show
  1. README.md +1 -1
  2. special_tokens_map.json +28 -4
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +106 -32
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
 
2
  library_name: transformers
3
  license: mit
4
- base_model: DeepESP/gpt2-spanish
5
  tags:
6
  - generated_from_trainer
7
  model-index:
 
1
  ---
2
+ base_model: DeepESP/gpt2-spanish
3
  library_name: transformers
4
  license: mit
 
5
  tags:
6
  - generated_from_trainer
7
  model-index:
special_tokens_map.json CHANGED
@@ -11,8 +11,32 @@
11
  "<|ax8|>",
12
  "<|ax9|>"
13
  ],
14
- "bos_token": "<|endoftext|>",
15
- "eos_token": "<|endoftext|>",
16
- "pad_token": "<|endoftext|>",
17
- "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
18
  }
 
11
  "<|ax8|>",
12
  "<|ax9|>"
13
  ],
14
+ "bos_token": {
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "eos_token": {
22
+ "content": "<|endoftext|>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "pad_token": {
29
+ "content": "<|endoftext|>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ },
35
+ "unk_token": {
36
+ "content": "<|endoftext|>",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false
41
+ }
42
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,41 +1,115 @@
1
  {
2
  "add_bos_token": false,
3
  "add_prefix_space": false,
4
- "bos_token": {
5
- "__type": "AddedToken",
6
- "content": "<|endoftext|>",
7
- "lstrip": false,
8
- "normalized": true,
9
- "rstrip": false,
10
- "single_word": false
11
- },
12
- "clean_up_tokenization_spaces": true,
13
- "eos_token": {
14
- "__type": "AddedToken",
15
- "content": "<|endoftext|>",
16
- "lstrip": false,
17
- "normalized": true,
18
- "rstrip": false,
19
- "single_word": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
20
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21
  "errors": "replace",
22
  "full_tokenizer_file": null,
23
  "model_max_length": 1000000000000000019884624838656,
24
- "pad_token": {
25
- "__type": "AddedToken",
26
- "content": "<|endoftext|>",
27
- "lstrip": false,
28
- "normalized": true,
29
- "rstrip": false,
30
- "single_word": false
31
- },
32
  "tokenizer_class": "GPT2Tokenizer",
33
- "unk_token": {
34
- "__type": "AddedToken",
35
- "content": "<|endoftext|>",
36
- "lstrip": false,
37
- "normalized": true,
38
- "rstrip": false,
39
- "single_word": false
40
- }
41
  }
 
1
  {
2
  "add_bos_token": false,
3
  "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<|talk|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<|ax1|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<|ax2|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<|ax3|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "4": {
38
+ "content": "<|ax4|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "5": {
46
+ "content": "<|ax5|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "6": {
54
+ "content": "<|ax6|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "7": {
62
+ "content": "<|ax7|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "8": {
70
+ "content": "<|ax8|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "9": {
78
+ "content": "<|ax9|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "50256": {
86
+ "content": "<|endoftext|>",
87
+ "lstrip": false,
88
+ "normalized": true,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ }
93
  },
94
+ "additional_special_tokens": [
95
+ "<|talk|>",
96
+ "<|ax1|>",
97
+ "<|ax2|>",
98
+ "<|ax3|>",
99
+ "<|ax4|>",
100
+ "<|ax5|>",
101
+ "<|ax6|>",
102
+ "<|ax7|>",
103
+ "<|ax8|>",
104
+ "<|ax9|>"
105
+ ],
106
+ "bos_token": "<|endoftext|>",
107
+ "clean_up_tokenization_spaces": false,
108
+ "eos_token": "<|endoftext|>",
109
  "errors": "replace",
110
  "full_tokenizer_file": null,
111
  "model_max_length": 1000000000000000019884624838656,
112
+ "pad_token": "<|endoftext|>",
 
 
 
 
 
 
 
113
  "tokenizer_class": "GPT2Tokenizer",
114
+ "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
115
  }