Hugging Face's logo

IronOne-AI-Labs
/
led-large-annual-report-QLoRA-fine-tuned-v0.7-merged

Text2Text Generation
Transformers
Safetensors
led
Inference Endpoints
Model card Files Community
theekshana commited on
Commit
cc82e7f
•
1 Parent(s): ded9ca8

Upload tokenizer

Browse files
Files changed (6) hide show
  1. added_tokens.json +4 -0
  2. merges.txt +0 -0
  3. special_tokens_map.json +49 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +85 -0
  6. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|im_end|>": 50266,
3
+ "<|im_start|>": 50265
4
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "bos_token": "<|im_start|>",
19
+ "cls_token": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "eos_token": "<|im_end|>",
27
+ "mask_token": {
28
+ "content": "<mask>",
29
+ "lstrip": true,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "pad_token": "<|im_end|>",
35
+ "sep_token": {
36
+ "content": "</s>",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false
41
+ },
42
+ "unk_token": {
43
+ "content": "<unk>",
44
+ "lstrip": false,
45
+ "normalized": true,
46
+ "rstrip": false,
47
+ "single_word": false
48
+ }
49
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "50265": {
45
+ "content": "<|im_start|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "50266": {
53
+ "content": "<|im_end|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ }
60
+ },
61
+ "additional_special_tokens": [
62
+ "<|im_start|>",
63
+ "<|im_end|>"
64
+ ],
65
+ "bos_token": "<|im_start|>",
66
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
67
+ "clean_up_tokenization_spaces": true,
68
+ "cls_token": "<s>",
69
+ "eos_token": "<|im_end|>",
70
+ "errors": "replace",
71
+ "mask_token": "<mask>",
72
+ "max_length": 1024,
73
+ "model_max_length": 16384,
74
+ "pad_to_multiple_of": null,
75
+ "pad_token": "<|im_end|>",
76
+ "pad_token_type_id": 0,
77
+ "padding_side": "right",
78
+ "sep_token": "</s>",
79
+ "stride": 0,
80
+ "tokenizer_class": "LEDTokenizer",
81
+ "trim_offsets": true,
82
+ "truncation_side": "right",
83
+ "truncation_strategy": "longest_first",
84
+ "unk_token": "<unk>"
85
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff