Hugging Face's logo

linhvy
/
TinyLlama_1B_sentiment

Transformers
Safetensors
Model card Files
xet
Community
linhvy commited on
Commit
2ee7d78
·
verified ·
1 Parent(s): ba990d4

Upload tokenizer

Browse files
Files changed (4) hide show
  1. chat_template.jinja +15 -0
  2. special_tokens_map.json +61 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +90 -0
chat_template.jinja ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {% for message in messages %}
2
+ {% if message['role'] == 'user' %}
3
+ {{ '<|user|>
4
+ ' + message['content'] + eos_token }}
5
+ {% elif message['role'] == 'system' %}
6
+ {{ '<|system|>
7
+ ' + message['content'] + eos_token }}
8
+ {% elif message['role'] == 'assistant' %}
9
+ {{ '<|assistant|>
10
+ ' + message['content'] + eos_token }}
11
+ {% endif %}
12
+ {% if loop.last and add_generation_prompt %}
13
+ {{ '<|assistant|>' }}
14
+ {% endif %}
15
+ {% endfor %}
special_tokens_map.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|im_start|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|im_end|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<|im_start|>system",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "<|im_start|>user",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "<|im_start|>assistant",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ }
38
+ ],
39
+ "bos_token": {
40
+ "content": "<s>",
41
+ "lstrip": false,
42
+ "normalized": false,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "eos_token": {
47
+ "content": "</s>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ },
53
+ "pad_token": "</s>",
54
+ "unk_token": {
55
+ "content": "<unk>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false
60
+ }
61
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
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": "<|im_start|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|im_end|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|im_start|>system",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|im_start|>user",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|im_start|>assistant",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ }
70
+ },
71
+ "additional_special_tokens": [
72
+ "<|im_start|>",
73
+ "<|im_end|>",
74
+ "<|im_start|>system",
75
+ "<|im_start|>user",
76
+ "<|im_start|>assistant"
77
+ ],
78
+ "bos_token": "<s>",
79
+ "clean_up_tokenization_spaces": false,
80
+ "eos_token": "</s>",
81
+ "extra_special_tokens": {},
82
+ "legacy": false,
83
+ "model_max_length": 2048,
84
+ "pad_token": "</s>",
85
+ "padding_side": "left",
86
+ "sp_model_kwargs": {},
87
+ "tokenizer_class": "LlamaTokenizerFast",
88
+ "unk_token": "<unk>",
89
+ "use_default_system_prompt": false
90
+ }