Hugging Face's logo

uild42
/
baby_mamba

PyTorch
Model card Files
xet
Community
uild42 commited on
Commit
8959c23
·
1 Parent(s): b568d97

commit files to HF hub

Browse files
Files changed (6) hide show
  1. merges.txt +0 -0
  2. pytorch_model.bin +1 -1
  3. special_tokens_map.json +3 -3
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +197 -5
  6. vocab.json +0 -0
merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6bc3db4822ddf39ec05738b7d861951d2d5444e98c968fbe456ba9d9f154dfc7
3
  size 275187300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa9798ec49dc2df2196e135ffd0bede856b1f070817c8f7d0ef0784aeee4225a
3
  size 275187300
special_tokens_map.json CHANGED
@@ -2,21 +2,21 @@
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
  "unk_token": {
17
  "content": "<|endoftext|>",
18
  "lstrip": false,
19
- "normalized": true,
20
  "rstrip": false,
21
  "single_word": false
22
  }
 
2
  "bos_token": {
3
  "content": "<|endoftext|>",
4
  "lstrip": false,
5
+ "normalized": false,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "eos_token": {
10
  "content": "<|endoftext|>",
11
  "lstrip": false,
12
+ "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
  "unk_token": {
17
  "content": "<|endoftext|>",
18
  "lstrip": false,
19
+ "normalized": false,
20
  "rstrip": false,
21
  "single_word": false
22
  }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,23 +1,215 @@
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
  },
14
  "bos_token": "<|endoftext|>",
15
  "clean_up_tokenization_spaces": false,
16
  "eos_token": "<|endoftext|>",
17
- "errors": "replace",
18
  "extra_special_tokens": {},
19
- "model_max_length": 1024,
20
  "pad_token": null,
21
- "tokenizer_class": "GPT2Tokenizer",
22
  "unk_token": "<|endoftext|>"
23
  }
 
1
  {
2
  "add_bos_token": false,
3
+ "add_eos_token": false,
4
  "add_prefix_space": false,
5
  "added_tokens_decoder": {
6
+ "0": {
7
  "content": "<|endoftext|>",
8
  "lstrip": false,
9
+ "normalized": false,
10
  "rstrip": false,
11
  "single_word": false,
12
  "special": true
13
+ },
14
+ "1": {
15
+ "content": "<|padding|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "50254": {
23
+ "content": " ",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "50255": {
31
+ "content": " ",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": false
37
+ },
38
+ "50256": {
39
+ "content": " ",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": false
45
+ },
46
+ "50257": {
47
+ "content": " ",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": false
53
+ },
54
+ "50258": {
55
+ "content": " ",
56
+ "lstrip": false,
57
+ "normalized": true,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "50259": {
63
+ "content": " ",
64
+ "lstrip": false,
65
+ "normalized": true,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": false
69
+ },
70
+ "50260": {
71
+ "content": " ",
72
+ "lstrip": false,
73
+ "normalized": true,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "50261": {
79
+ "content": " ",
80
+ "lstrip": false,
81
+ "normalized": true,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": false
85
+ },
86
+ "50262": {
87
+ "content": " ",
88
+ "lstrip": false,
89
+ "normalized": true,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "50263": {
95
+ "content": " ",
96
+ "lstrip": false,
97
+ "normalized": true,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": false
101
+ },
102
+ "50264": {
103
+ "content": " ",
104
+ "lstrip": false,
105
+ "normalized": true,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": false
109
+ },
110
+ "50265": {
111
+ "content": " ",
112
+ "lstrip": false,
113
+ "normalized": true,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": false
117
+ },
118
+ "50266": {
119
+ "content": " ",
120
+ "lstrip": false,
121
+ "normalized": true,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "50267": {
127
+ "content": " ",
128
+ "lstrip": false,
129
+ "normalized": true,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "50268": {
135
+ "content": " ",
136
+ "lstrip": false,
137
+ "normalized": true,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "50269": {
143
+ "content": " ",
144
+ "lstrip": false,
145
+ "normalized": true,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "50270": {
151
+ "content": " ",
152
+ "lstrip": false,
153
+ "normalized": true,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "50271": {
159
+ "content": " ",
160
+ "lstrip": false,
161
+ "normalized": true,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "50272": {
167
+ "content": " ",
168
+ "lstrip": false,
169
+ "normalized": true,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "50273": {
175
+ "content": " ",
176
+ "lstrip": false,
177
+ "normalized": true,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "50274": {
183
+ "content": " ",
184
+ "lstrip": false,
185
+ "normalized": true,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": false
189
+ },
190
+ "50275": {
191
+ "content": " ",
192
+ "lstrip": false,
193
+ "normalized": true,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": false
197
+ },
198
+ "50276": {
199
+ "content": " ",
200
+ "lstrip": false,
201
+ "normalized": true,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": false
205
  }
206
  },
207
  "bos_token": "<|endoftext|>",
208
  "clean_up_tokenization_spaces": false,
209
  "eos_token": "<|endoftext|>",
 
210
  "extra_special_tokens": {},
211
+ "model_max_length": 1000000000000000019884624838656,
212
  "pad_token": null,
213
+ "tokenizer_class": "GPTNeoXTokenizer",
214
  "unk_token": "<|endoftext|>"
215
  }
vocab.json DELETED
The diff for this file is too large to render. See raw diff