Hugging Face's logo

tarekxpc
/
mamba_text_classification

Transformers
PyTorch
Generated from Trainer
Inference Endpoints
Model card Files Community
tarekxpc commited on
Commit
94129f3
•
1 Parent(s): 1d9ccef

Training in progress, step 125

Browse files
Files changed (5) hide show
  1. pytorch_model.bin +1 -1
  2. special_tokens_map.json +4 -25
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +183 -30
  5. training_args.bin +1 -1
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:300f19432f02b1201b3df61eea202180776ff72383dd406bcc02d66757620ff7
3
  size 516674074
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcb000553029ed40af8ad96fcd96876f77365f766c905167602369c78c05494c
3
  size 516674074
special_tokens_map.json CHANGED
@@ -1,42 +1,21 @@
1
  {
2
  "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "cls_token": {
10
- "content": "<s>",
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
  "eos_token": {
17
- "content": "</s>",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
- "mask_token": {
24
- "content": "<mask>",
25
- "lstrip": false,
26
- "normalized": false,
27
- "rstrip": false,
28
- "single_word": false
29
- },
30
- "pad_token": "</s>",
31
- "sep_token": {
32
- "content": "</s>",
33
  "lstrip": false,
34
  "normalized": false,
35
  "rstrip": false,
36
  "single_word": false
37
  },
 
38
  "unk_token": {
39
- "content": "<unk>",
40
  "lstrip": false,
41
  "normalized": false,
42
  "rstrip": false,
 
1
  {
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
+ "pad_token": "<|endoftext|>",
17
  "unk_token": {
18
+ "content": "<|endoftext|>",
19
  "lstrip": false,
20
  "normalized": false,
21
  "rstrip": false,
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,7 +1,10 @@
1
  {
 
 
 
2
  "added_tokens_decoder": {
3
  "0": {
4
- "content": "<pad>",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
@@ -9,53 +12,203 @@
9
  "special": true
10
  },
11
  "1": {
12
- "content": "<s>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
- "2": {
20
- "content": "</s>",
21
  "lstrip": false,
22
- "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
- "special": true
26
  },
27
- "3": {
28
- "content": "<unk>",
29
  "lstrip": false,
30
- "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
- "special": true
34
  },
35
- "4": {
36
- "content": "<mask>",
37
  "lstrip": false,
38
- "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
- "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42
  }
43
  },
44
- "bos_token": "<s>",
45
  "clean_up_tokenization_spaces": true,
46
- "cls_token": "<s>",
47
- "eos_token": "</s>",
48
- "mask_token": "<mask>",
49
- "max_length": 512,
50
- "model_max_length": 512,
51
- "pad_to_multiple_of": null,
52
- "pad_token": "</s>",
53
- "pad_token_type_id": 0,
54
- "padding_side": "right",
55
- "sep_token": "</s>",
56
- "stride": 0,
57
- "tokenizer_class": "PreTrainedTokenizerFast",
58
- "truncation_side": "right",
59
- "truncation_strategy": "longest_first",
60
- "unk_token": "<unk>"
61
  }
 
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,
 
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": true,
209
+ "eos_token": "<|endoftext|>",
210
+ "model_max_length": 1000,
211
+ "pad_token": "<|endoftext|>",
212
+ "tokenizer_class": "GPTNeoXTokenizer",
213
+ "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
 
 
 
214
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3cb40029289c5707c80e5a84c167a3cac1ada38530b90f1c9d5e99d150a43cf
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd0e2545d4c0b92e26986e208bcf484d9e13b5da2a08dbb03f09baf9c0fc12a1
3
  size 4984