Hugging Face's logo

stanpony
/
test_1M_1-2025-02-20-22-04_full

Text Generation
Transformers
Safetensors
gpt_neo
Model card Files Community
stanpony commited on
Commit
4b3e50c
·
verified ·
1 Parent(s): 50a6b23

Upload tokenizer

Browse files
Files changed (6) hide show
  1. added_tokens.json +20 -0
  2. merges.txt +0 -0
  3. special_tokens_map.json +24 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +169 -0
  6. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<cluster_0>": 50268,
3
+ "<cluster_10>": 50264,
4
+ "<cluster_11>": 50261,
5
+ "<cluster_12>": 50257,
6
+ "<cluster_13>": 50265,
7
+ "<cluster_14>": 50262,
8
+ "<cluster_15>": 50272,
9
+ "<cluster_1>": 50260,
10
+ "<cluster_2>": 50259,
11
+ "<cluster_3>": 50269,
12
+ "<cluster_4>": 50267,
13
+ "<cluster_5>": 50270,
14
+ "<cluster_6>": 50266,
15
+ "<cluster_7>": 50263,
16
+ "<cluster_8>": 50271,
17
+ "<cluster_9>": 50258,
18
+ "<start_reasoning>": 50273,
19
+ "<stop_reasoning>": 50274
20
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,169 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": true,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "50256": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "50257": {
15
+ "content": "<cluster_12>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": false
21
+ },
22
+ "50258": {
23
+ "content": "<cluster_9>",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "50259": {
31
+ "content": "<cluster_2>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": false
37
+ },
38
+ "50260": {
39
+ "content": "<cluster_1>",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "50261": {
47
+ "content": "<cluster_11>",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "50262": {
55
+ "content": "<cluster_14>",
56
+ "lstrip": false,
57
+ "normalized": true,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "50263": {
63
+ "content": "<cluster_7>",
64
+ "lstrip": false,
65
+ "normalized": true,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": false
69
+ },
70
+ "50264": {
71
+ "content": "<cluster_10>",
72
+ "lstrip": false,
73
+ "normalized": true,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "50265": {
79
+ "content": "<cluster_13>",
80
+ "lstrip": false,
81
+ "normalized": true,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": false
85
+ },
86
+ "50266": {
87
+ "content": "<cluster_6>",
88
+ "lstrip": false,
89
+ "normalized": true,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "50267": {
95
+ "content": "<cluster_4>",
96
+ "lstrip": false,
97
+ "normalized": true,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": false
101
+ },
102
+ "50268": {
103
+ "content": "<cluster_0>",
104
+ "lstrip": false,
105
+ "normalized": true,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": false
109
+ },
110
+ "50269": {
111
+ "content": "<cluster_3>",
112
+ "lstrip": false,
113
+ "normalized": true,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": false
117
+ },
118
+ "50270": {
119
+ "content": "<cluster_5>",
120
+ "lstrip": false,
121
+ "normalized": true,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "50271": {
127
+ "content": "<cluster_8>",
128
+ "lstrip": false,
129
+ "normalized": true,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "50272": {
135
+ "content": "<cluster_15>",
136
+ "lstrip": false,
137
+ "normalized": true,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "50273": {
143
+ "content": "<start_reasoning>",
144
+ "lstrip": false,
145
+ "normalized": true,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "50274": {
151
+ "content": "<stop_reasoning>",
152
+ "lstrip": false,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ }
158
+ },
159
+ "bos_token": "<|endoftext|>",
160
+ "clean_up_tokenization_spaces": false,
161
+ "eos_token": "<|endoftext|>",
162
+ "errors": "replace",
163
+ "extra_special_tokens": {},
164
+ "model_max_length": 2048,
165
+ "pad_token": "<|endoftext|>",
166
+ "padding_side": "right",
167
+ "tokenizer_class": "GPT2Tokenizer",
168
+ "unk_token": "<|endoftext|>"
169
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff