Hugging Face's logo

Mattimax
/
SmolLM2-135M-Instruct-Ita

Safetensors
llama
Model card Files
xet
Community
Mattimax commited on
Commit
771a73b
·
verified ·
1 Parent(s): 2705da7

Update tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +142 -51
tokenizer_config.json CHANGED
@@ -1,63 +1,154 @@
1
  {
2
  "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
- "0": { "content": "<|endoftext|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true },
5
- "1": { "content": "<|im_start|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true },
6
- "2": { "content": "<|im_end|>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true },
7
- "3": { "content": "<repo_name>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true },
8
- "4": { "content": "<reponame>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true },
9
- "5": { "content": "<file_sep>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true },
10
- "6": { "content": "<filename>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true },
11
- "7": { "content": "<gh_stars>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true },
12
- "8": { "content": "<issue_start>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true },
13
- "9": { "content": "<issue_comment>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true },
14
- "10": { "content": "<issue_closed>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true },
15
- "11": { "content": "<jupyter_start>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true },
16
- "12": { "content": "<jupyter_text>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true },
17
- "13": { "content": "<jupyter_code>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true },
18
- "14": { "content": "<jupyter_output>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true },
19
- "15": { "content": "<jupyter_script>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true },
20
- "16": { "content": "<empty_output>", "lstrip": false, "normalized": false, "rstrip": false, "single_word": false, "special": true }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21
  },
22
  "additional_special_tokens": [
23
- "<|endoftext|>",
24
  "<|im_start|>",
25
- "<|im_end|>",
26
- "<repo_name>",
27
- "<reponame>",
28
- "<file_sep>",
29
- "<filename>",
30
- "<gh_stars>",
31
- "<issue_start>",
32
- "<issue_comment>",
33
- "<issue_closed>",
34
- "<jupyter_start>",
35
- "<jupyter_text>",
36
- "<jupyter_code>",
37
- "<jupyter_output>",
38
- "<jupyter_script>",
39
- "<empty_output>"
40
  ],
41
- "bos_token": "<|endoftext|>",
 
42
  "clean_up_tokenization_spaces": false,
43
- "eos_token": "<|endoftext|>",
44
- "extra_special_tokens": {},
45
- "max_length": 256,
46
  "model_max_length": 8192,
47
- "pad_to_multiple_of": null,
48
- "pad_token": "<|endoftext|>",
49
- "pad_token_type_id": 0,
50
- "padding_side": "right",
51
- "stride": 0,
52
  "tokenizer_class": "GPT2Tokenizer",
53
- "truncation_side": "right",
54
- "truncation_strategy": "longest_first",
55
  "unk_token": "<|endoftext|>",
56
- "vocab_size": 49152,
57
-
58
- "chat_template": {
59
- "system": "<<SYS>>\n{system_prompt}\n<</SYS>>\n\n",
60
- "user": "<|im_start|>utente: {user_prompt}<|im_end|>\n",
61
- "assistant": "<|im_start|>assistente: {assistant_response}<|im_end|>"
62
- }
63
  }
 
1
  {
2
  "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<repo_name>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<reponame>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<file_sep>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<filename>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": "<gh_stars>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": "<issue_start>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": "<issue_comment>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": "<issue_closed>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<jupyter_start>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "12": {
101
+ "content": "<jupyter_text>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "13": {
109
+ "content": "<jupyter_code>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "14": {
117
+ "content": "<jupyter_output>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "15": {
125
+ "content": "<jupyter_script>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "16": {
133
+ "content": "<empty_output>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ }
140
  },
141
  "additional_special_tokens": [
 
142
  "<|im_start|>",
143
+ "<|im_end|>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
144
  ],
145
+ "bos_token": "<|im_start|>",
146
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named DATA-AI, trained by M.INC.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
147
  "clean_up_tokenization_spaces": false,
148
+ "eos_token": "<|im_end|>",
 
 
149
  "model_max_length": 8192,
150
+ "pad_token": "<|im_end|>",
 
 
 
 
151
  "tokenizer_class": "GPT2Tokenizer",
 
 
152
  "unk_token": "<|endoftext|>",
153
+ "vocab_size": 49152
 
 
 
 
 
 
154
  }