Hugging Face's logo

Nared45
/
part4

Text Generation
Transformers
Safetensors
llama
conversational
text-generation-inference
Model card Files
xet
 Community
Nared45 commited on
Commit
e1a9eee
·
verified ·
1 Parent(s): f6baeb6

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +3 -3
  2. tokenizer.json +3 -12
  3. tokenizer_config.json +5 -11
special_tokens_map.json CHANGED
@@ -2,14 +2,14 @@
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
  },
@@ -17,7 +17,7 @@
17
  "unk_token": {
18
  "content": "<unk>",
19
  "lstrip": false,
20
- "normalized": true,
21
  "rstrip": false,
22
  "single_word": false
23
  }
 
2
  "bos_token": {
3
  "content": "<s>",
4
  "lstrip": false,
5
+ "normalized": false,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "eos_token": {
10
  "content": "</s>",
11
  "lstrip": false,
12
+ "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
 
17
  "unk_token": {
18
  "content": "<unk>",
19
  "lstrip": false,
20
+ "normalized": false,
21
  "rstrip": false,
22
  "single_word": false
23
  }
tokenizer.json CHANGED
@@ -9,7 +9,7 @@
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
12
- "normalized": true,
13
  "special": true
14
  },
15
  {
@@ -18,7 +18,7 @@
18
  "single_word": false,
19
  "lstrip": false,
20
  "rstrip": false,
21
- "normalized": true,
22
  "special": true
23
  },
24
  {
@@ -27,20 +27,11 @@
27
  "single_word": false,
28
  "lstrip": false,
29
  "rstrip": false,
30
- "normalized": true,
31
  "special": true
32
  },
33
  {
34
  "id": 32000,
35
- "content": "<pad>",
36
- "single_word": false,
37
- "lstrip": false,
38
- "rstrip": false,
39
- "normalized": true,
40
- "special": false
41
- },
42
- {
43
- "id": 32001,
44
  "content": "[PAD]",
45
  "single_word": false,
46
  "lstrip": false,
 
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
12
+ "normalized": false,
13
  "special": true
14
  },
15
  {
 
18
  "single_word": false,
19
  "lstrip": false,
20
  "rstrip": false,
21
+ "normalized": false,
22
  "special": true
23
  },
24
  {
 
27
  "single_word": false,
28
  "lstrip": false,
29
  "rstrip": false,
30
+ "normalized": false,
31
  "special": true
32
  },
33
  {
34
  "id": 32000,
 
 
 
 
 
 
 
 
 
35
  "content": "[PAD]",
36
  "single_word": false,
37
  "lstrip": false,
tokenizer_config.json CHANGED
@@ -6,7 +6,7 @@
6
  "0": {
7
  "content": "<unk>",
8
  "lstrip": false,
9
- "normalized": true,
10
  "rstrip": false,
11
  "single_word": false,
12
  "special": true
@@ -14,7 +14,7 @@
14
  "1": {
15
  "content": "<s>",
16
  "lstrip": false,
17
- "normalized": true,
18
  "rstrip": false,
19
  "single_word": false,
20
  "special": true
@@ -22,20 +22,12 @@
22
  "2": {
23
  "content": "</s>",
24
  "lstrip": false,
25
- "normalized": true,
26
  "rstrip": false,
27
  "single_word": false,
28
  "special": true
29
  },
30
  "32000": {
31
- "content": "<pad>",
32
- "lstrip": false,
33
- "normalized": true,
34
- "rstrip": false,
35
- "single_word": false,
36
- "special": false
37
- },
38
- "32001": {
39
  "content": "[PAD]",
40
  "lstrip": false,
41
  "normalized": false,
@@ -45,11 +37,13 @@
45
  }
46
  },
47
  "bos_token": "<s>",
 
48
  "clean_up_tokenization_spaces": false,
49
  "eos_token": "</s>",
50
  "legacy": false,
51
  "model_max_length": 1000000000000000019884624838656,
52
  "pad_token": "</s>",
 
53
  "sp_model_kwargs": {},
54
  "tokenizer_class": "LlamaTokenizer",
55
  "unk_token": "<unk>",
 
6
  "0": {
7
  "content": "<unk>",
8
  "lstrip": false,
9
+ "normalized": false,
10
  "rstrip": false,
11
  "single_word": false,
12
  "special": true
 
14
  "1": {
15
  "content": "<s>",
16
  "lstrip": false,
17
+ "normalized": false,
18
  "rstrip": false,
19
  "single_word": false,
20
  "special": true
 
22
  "2": {
23
  "content": "</s>",
24
  "lstrip": false,
25
+ "normalized": false,
26
  "rstrip": false,
27
  "single_word": false,
28
  "special": true
29
  },
30
  "32000": {
 
 
 
 
 
 
 
 
31
  "content": "[PAD]",
32
  "lstrip": false,
33
  "normalized": false,
 
37
  }
38
  },
39
  "bos_token": "<s>",
40
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
41
  "clean_up_tokenization_spaces": false,
42
  "eos_token": "</s>",
43
  "legacy": false,
44
  "model_max_length": 1000000000000000019884624838656,
45
  "pad_token": "</s>",
46
+ "padding_side": "right",
47
  "sp_model_kwargs": {},
48
  "tokenizer_class": "LlamaTokenizer",
49
  "unk_token": "<unk>",