Hugging Face's logo

cafierom
/
bert-base-cased-finetuned-AddedTokens-HMGCR-IC50s-V1

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
cafierom commited on
Commit
a75db93
·
verified ·
1 Parent(s): 4708c46

Training in progress, epoch 1

Browse files
Files changed (6) hide show
  1. added_tokens.json +11 -0
  2. config.json +1 -1
  3. model.safetensors +2 -2
  4. tokenizer.json +81 -0
  5. tokenizer_config.json +72 -0
  6. training_args.bin +1 -1
added_tokens.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "(=O)": 29004,
3
+ "(Cl)": 29000,
4
+ "(F)": 28998,
5
+ "([N+]([O-])=O)": 29002,
6
+ "N#C": 29003,
7
+ "[C@@H]": 28997,
8
+ "[C@H]": 28996,
9
+ "c1": 28999,
10
+ "c2": 29001
11
+ }
config.json CHANGED
@@ -33,5 +33,5 @@
33
  "transformers_version": "4.48.3",
34
  "type_vocab_size": 2,
35
  "use_cache": true,
36
- "vocab_size": 28996
37
  }
 
33
  "transformers_version": "4.48.3",
34
  "type_vocab_size": 2,
35
  "use_cache": true,
36
+ "vocab_size": 29005
37
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee27364d0dc57fb121865b06b69be137387e7abc5c27cc53b5bb4f7580e86d5f
3
- size 433273844
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08927257b102546b69ac2b84eb358c13b69de174a7fd5cdd88365f740464ca3c
3
+ size 433301492
tokenizer.json CHANGED
@@ -59,6 +59,87 @@
59
  "rstrip": false,
60
  "normalized": false,
61
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
62
  }
63
  ],
64
  "normalizer": {
 
59
  "rstrip": false,
60
  "normalized": false,
61
  "special": true
62
+ },
63
+ {
64
+ "id": 28996,
65
+ "content": "[C@H]",
66
+ "single_word": false,
67
+ "lstrip": false,
68
+ "rstrip": false,
69
+ "normalized": true,
70
+ "special": false
71
+ },
72
+ {
73
+ "id": 28997,
74
+ "content": "[C@@H]",
75
+ "single_word": false,
76
+ "lstrip": false,
77
+ "rstrip": false,
78
+ "normalized": true,
79
+ "special": false
80
+ },
81
+ {
82
+ "id": 28998,
83
+ "content": "(F)",
84
+ "single_word": false,
85
+ "lstrip": false,
86
+ "rstrip": false,
87
+ "normalized": true,
88
+ "special": false
89
+ },
90
+ {
91
+ "id": 28999,
92
+ "content": "c1",
93
+ "single_word": false,
94
+ "lstrip": false,
95
+ "rstrip": false,
96
+ "normalized": true,
97
+ "special": false
98
+ },
99
+ {
100
+ "id": 29000,
101
+ "content": "(Cl)",
102
+ "single_word": false,
103
+ "lstrip": false,
104
+ "rstrip": false,
105
+ "normalized": true,
106
+ "special": false
107
+ },
108
+ {
109
+ "id": 29001,
110
+ "content": "c2",
111
+ "single_word": false,
112
+ "lstrip": false,
113
+ "rstrip": false,
114
+ "normalized": true,
115
+ "special": false
116
+ },
117
+ {
118
+ "id": 29002,
119
+ "content": "([N+]([O-])=O)",
120
+ "single_word": false,
121
+ "lstrip": false,
122
+ "rstrip": false,
123
+ "normalized": true,
124
+ "special": false
125
+ },
126
+ {
127
+ "id": 29003,
128
+ "content": "N#C",
129
+ "single_word": false,
130
+ "lstrip": false,
131
+ "rstrip": false,
132
+ "normalized": true,
133
+ "special": false
134
+ },
135
+ {
136
+ "id": 29004,
137
+ "content": "(=O)",
138
+ "single_word": false,
139
+ "lstrip": false,
140
+ "rstrip": false,
141
+ "normalized": true,
142
+ "special": false
143
  }
144
  ],
145
  "normalizer": {
tokenizer_config.json CHANGED
@@ -39,6 +39,78 @@
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42
  }
43
  },
44
  "clean_up_tokenization_spaces": false,
 
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
42
+ },
43
+ "28996": {
44
+ "content": "[C@H]",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "28997": {
52
+ "content": "[C@@H]",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "28998": {
60
+ "content": "(F)",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "28999": {
68
+ "content": "c1",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "29000": {
76
+ "content": "(Cl)",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "29001": {
84
+ "content": "c2",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "29002": {
92
+ "content": "([N+]([O-])=O)",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "29003": {
100
+ "content": "N#C",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "29004": {
108
+ "content": "(=O)",
109
+ "lstrip": false,
110
+ "normalized": true,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
  }
115
  },
116
  "clean_up_tokenization_spaces": false,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc2f66fea85b3be406a817fc0cda9d8ec157d0c29fbd5831fc2f3927ed199fbb
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38f55031f2cdeb40c67c50c35380ca6eb049a385d96f3b84354fbcd615134fb6
3
  size 5368