Hugging Face's logo

Moatazz
/
fourthtrial

Text Generation
Transformers
Safetensors
llama
conversational
text-generation-inference
Model card Files
xet
 Community
Moatazz commited on
Commit
72e6ea3
·
verified ·
1 Parent(s): 28998ac

Upload tokenizer

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +3 -4
  2. tokenizer.json +4 -18
  3. tokenizer.model +3 -0
  4. tokenizer_config.json +8 -12
special_tokens_map.json CHANGED
@@ -2,22 +2,21 @@
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
  },
16
- "pad_token": "</s>",
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
  },
 
16
  "unk_token": {
17
  "content": "<unk>",
18
  "lstrip": false,
19
+ "normalized": false,
20
  "rstrip": false,
21
  "single_word": false
22
  }
tokenizer.json CHANGED
@@ -1,11 +1,6 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 1024,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
  "padding": null,
10
  "added_tokens": [
11
  {
@@ -14,7 +9,7 @@
14
  "single_word": false,
15
  "lstrip": false,
16
  "rstrip": false,
17
- "normalized": true,
18
  "special": true
19
  },
20
  {
@@ -23,7 +18,7 @@
23
  "single_word": false,
24
  "lstrip": false,
25
  "rstrip": false,
26
- "normalized": true,
27
  "special": true
28
  },
29
  {
@@ -32,17 +27,8 @@
32
  "single_word": false,
33
  "lstrip": false,
34
  "rstrip": false,
35
- "normalized": true,
36
  "special": true
37
- },
38
- {
39
- "id": 32000,
40
- "content": "<pad>",
41
- "single_word": false,
42
- "lstrip": false,
43
- "rstrip": false,
44
- "normalized": true,
45
- "special": false
46
  }
47
  ],
48
  "normalizer": {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
 
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
  "normalizer": {
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json CHANGED
@@ -1,9 +1,11 @@
1
  {
 
 
2
  "added_tokens_decoder": {
3
  "0": {
4
  "content": "<unk>",
5
  "lstrip": false,
6
- "normalized": true,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
@@ -11,7 +13,7 @@
11
  "1": {
12
  "content": "<s>",
13
  "lstrip": false,
14
- "normalized": true,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
@@ -19,26 +21,20 @@
19
  "2": {
20
  "content": "</s>",
21
  "lstrip": false,
22
- "normalized": true,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
- },
27
- "32000": {
28
- "content": "<pad>",
29
- "lstrip": false,
30
- "normalized": true,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": false
34
  }
35
  },
36
  "bos_token": "<s>",
 
37
  "clean_up_tokenization_spaces": false,
38
  "eos_token": "</s>",
39
  "legacy": false,
40
  "model_max_length": 1000000000000000019884624838656,
41
- "pad_token": "</s>",
 
42
  "sp_model_kwargs": {},
43
  "tokenizer_class": "LlamaTokenizer",
44
  "unk_token": "<unk>",
 
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
 
13
  "1": {
14
  "content": "<s>",
15
  "lstrip": false,
16
+ "normalized": false,
17
  "rstrip": false,
18
  "single_word": false,
19
  "special": true
 
21
  "2": {
22
  "content": "</s>",
23
  "lstrip": false,
24
+ "normalized": false,
25
  "rstrip": false,
26
  "single_word": false,
27
  "special": true
 
 
 
 
 
 
 
 
28
  }
29
  },
30
  "bos_token": "<s>",
31
+ "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 %}",
32
  "clean_up_tokenization_spaces": false,
33
  "eos_token": "</s>",
34
  "legacy": false,
35
  "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": null,
37
+ "padding_side": "right",
38
  "sp_model_kwargs": {},
39
  "tokenizer_class": "LlamaTokenizer",
40
  "unk_token": "<unk>",