Hugging Face's logo

ZhankuiHe
/
unicrs-rec

Transformers
Safetensors
Model card Files
xet
Community
ZhankuiHe commited on
Commit
dc53bee
·
verified ·
1 Parent(s): 52c1482

Upload tokenizer

Browse files
Files changed (16) hide show
  1. context/added_tokens.json +4 -0
  2. context/merges.txt +0 -0
  3. context/special_tokens_map.json +33 -0
  4. context/tokenizer.json +0 -0
  5. context/tokenizer_config.json +43 -0
  6. context/vocab.json +0 -0
  7. item/special_tokens_map.json +16 -0
  8. item/tokenizer.json +0 -0
  9. item/tokenizer_config.json +0 -0
  10. prompt/added_tokens.json +3 -0
  11. prompt/merges.txt +0 -0
  12. prompt/special_tokens_map.json +54 -0
  13. prompt/tokenizer.json +0 -0
  14. prompt/tokenizer_config.json +70 -0
  15. prompt/vocab.json +0 -0
  16. tokenizer_config.json +8 -0
context/added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<movie>": 50258,
3
+ "<pad>": 50257
4
+ }
context/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
context/special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<movie>"
4
+ ],
5
+ "bos_token": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "eos_token": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "pad_token": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "unk_token": {
27
+ "content": "<|endoftext|>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
context/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
context/tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "50256": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "50257": {
14
+ "content": "<pad>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "50258": {
22
+ "content": "<movie>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [
31
+ "<movie>"
32
+ ],
33
+ "bos_token": "<|endoftext|>",
34
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] }}{% elif message['role'] == 'assistant' %}{{ 'System: ' + message['content'] }}{% endif %}{{ eos_token }}{% endfor %}",
35
+ "clean_up_tokenization_spaces": true,
36
+ "eos_token": "<|endoftext|>",
37
+ "errors": "replace",
38
+ "model_max_length": 1024,
39
+ "pad_token": "<pad>",
40
+ "tokenizer_class": "GPT2Tokenizer",
41
+ "truncation_side": "left",
42
+ "unk_token": "<|endoftext|>"
43
+ }
context/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
item/special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "pad_token": {
3
+ "content": "[PAD]",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "unk_token": {
10
+ "content": "[UNK]",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ }
16
+ }
item/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
item/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
prompt/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<movie>": 50265
3
+ }
prompt/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
prompt/special_tokens_map.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<movie>"
4
+ ],
5
+ "bos_token": {
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "cls_token": {
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "eos_token": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "mask_token": {
27
+ "content": "<mask>",
28
+ "lstrip": true,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ },
33
+ "pad_token": {
34
+ "content": "<pad>",
35
+ "lstrip": false,
36
+ "normalized": true,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ },
40
+ "sep_token": {
41
+ "content": "</s>",
42
+ "lstrip": false,
43
+ "normalized": true,
44
+ "rstrip": false,
45
+ "single_word": false
46
+ },
47
+ "unk_token": {
48
+ "content": "<unk>",
49
+ "lstrip": false,
50
+ "normalized": true,
51
+ "rstrip": false,
52
+ "single_word": false
53
+ }
54
+ }
prompt/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
prompt/tokenizer_config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "50265": {
45
+ "content": "<movie>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ }
52
+ },
53
+ "additional_special_tokens": [
54
+ "<movie>"
55
+ ],
56
+ "bos_token": "<s>",
57
+ "chat_template": "{{cls_token}}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] }}{% elif message['role'] == 'assistant' %}{{ 'System: ' + message['content'] }}{% endif %}{{ sep_token }}{% endfor %}",
58
+ "clean_up_tokenization_spaces": true,
59
+ "cls_token": "<s>",
60
+ "eos_token": "</s>",
61
+ "errors": "replace",
62
+ "mask_token": "<mask>",
63
+ "model_max_length": 512,
64
+ "pad_token": "<pad>",
65
+ "sep_token": "</s>",
66
+ "tokenizer_class": "RobertaTokenizer",
67
+ "trim_offsets": true,
68
+ "truncation_side": "left",
69
+ "unk_token": "<unk>"
70
+ }
prompt/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "tokenizers": {
3
+ "item": "EntityTokenizer",
4
+ "context": "GPT2TokenizerFast",
5
+ "prompt": "RobertaTokenizerFast"
6
+ },
7
+ "tokenizer_key_for_decoding": "item"
8
+ }