Hugging Face's logo

tiiuae
/
falcon-mamba-7b

Text Generation
Transformers
Safetensors
English
falcon_mamba
Eval Results
Inference Endpoints
Model card Files Community
11
ybelkada commited on
Commit
7c4eb54
•
1 Parent(s): 3e1b10b

Update tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +115 -4
tokenizer_config.json CHANGED
@@ -1,8 +1,119 @@
1
  {
2
- "eos_token": "<|endoftext|>",
3
  "add_prefix_space": false,
4
- "model_max_length": 2048,
5
- "special_tokens_map_file": null,
6
- "name_or_path": "dd_alpha",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  "tokenizer_class": "PreTrainedTokenizerFast"
8
  }
 
1
  {
 
2
  "add_prefix_space": false,
3
+ "padding_side": "left",
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": ">>TITLE<<",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": ">>ABSTRACT<<",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": ">>INTRODUCTION<<",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": ">>SUMMARY<<",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "4": {
38
+ "content": ">>COMMENT<<",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "5": {
46
+ "content": ">>ANSWER<<",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "6": {
54
+ "content": ">>QUESTION<<",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "7": {
62
+ "content": ">>DOMAIN<<",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "8": {
70
+ "content": ">>PREFIX<<",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "9": {
78
+ "content": ">>SUFFIX<<",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "10": {
86
+ "content": ">>MIDDLE<<",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "11": {
94
+ "content": "<|endoftext|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ }
101
+ },
102
+ "additional_special_tokens": [
103
+ ">>TITLE<<",
104
+ ">>ABSTRACT<<",
105
+ ">>INTRODUCTION<<",
106
+ ">>SUMMARY<<",
107
+ ">>COMMENT<<",
108
+ ">>ANSWER<<",
109
+ ">>QUESTION<<",
110
+ ">>DOMAIN<<",
111
+ ">>PREFIX<<",
112
+ ">>SUFFIX<<",
113
+ ">>MIDDLE<<"
114
+ ],
115
+ "clean_up_tokenization_spaces": true,
116
+ "eos_token": "<|endoftext|>",
117
+ "model_max_length": 1000000000000000019884624838656,
118
  "tokenizer_class": "PreTrainedTokenizerFast"
119
  }