ZJU-Fangyin
commited on
Commit
•
a35016a
1
Parent(s):
b5c8dfa
Upload 7 files
Browse files- added_tokens.json +183 -0
- config.json +44 -0
- merges.txt +1 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +51 -0
- tokenizer_config.json +64 -0
- vocab.json +6 -0
added_tokens.json
ADDED
@@ -0,0 +1,183 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<mask>": 184,
|
3 |
+
"[#Branch1]": 12,
|
4 |
+
"[#Branch2]": 178,
|
5 |
+
"[#C-1]": 181,
|
6 |
+
"[#C]": 165,
|
7 |
+
"[#N+1]": 120,
|
8 |
+
"[#N]": 23,
|
9 |
+
"[#P]": 87,
|
10 |
+
"[#Ring1]": 128,
|
11 |
+
"[#S]": 40,
|
12 |
+
"[-/Ring1]": 129,
|
13 |
+
"[-/Ring2]": 156,
|
14 |
+
"[-\\Ring1]": 164,
|
15 |
+
"[-\\Ring2]": 34,
|
16 |
+
"[/123I]": 7,
|
17 |
+
"[/B]": 125,
|
18 |
+
"[/Br]": 149,
|
19 |
+
"[/C-1]": 68,
|
20 |
+
"[/C@@H1]": 13,
|
21 |
+
"[/C@@]": 14,
|
22 |
+
"[/C@H1]": 177,
|
23 |
+
"[/C@]": 31,
|
24 |
+
"[/CH0]": 126,
|
25 |
+
"[/CH1-1]": 88,
|
26 |
+
"[/CH1]": 10,
|
27 |
+
"[/C]": 118,
|
28 |
+
"[/Cl]": 155,
|
29 |
+
"[/F]": 6,
|
30 |
+
"[/I]": 83,
|
31 |
+
"[/N+1]": 152,
|
32 |
+
"[/NH0]": 55,
|
33 |
+
"[/NH1]": 24,
|
34 |
+
"[/N]": 67,
|
35 |
+
"[/O-1]": 171,
|
36 |
+
"[/OH0]": 174,
|
37 |
+
"[/O]": 69,
|
38 |
+
"[/P@@]": 16,
|
39 |
+
"[/P]": 79,
|
40 |
+
"[/S+1]": 47,
|
41 |
+
"[/S@@+1]": 21,
|
42 |
+
"[/S@@]": 160,
|
43 |
+
"[/S@]": 77,
|
44 |
+
"[/S]": 112,
|
45 |
+
"[/Si]": 38,
|
46 |
+
"[11CH3]": 107,
|
47 |
+
"[123I]": 124,
|
48 |
+
"[124I]": 136,
|
49 |
+
"[125I]": 39,
|
50 |
+
"[127I]": 36,
|
51 |
+
"[17F]": 143,
|
52 |
+
"[18F]": 97,
|
53 |
+
"[18OH1]": 76,
|
54 |
+
"[3H]": 137,
|
55 |
+
"[=B]": 25,
|
56 |
+
"[=Branch1]": 33,
|
57 |
+
"[=Branch2]": 100,
|
58 |
+
"[=CH0]": 78,
|
59 |
+
"[=C]": 35,
|
60 |
+
"[=N+1]": 144,
|
61 |
+
"[=N-1]": 161,
|
62 |
+
"[=NH0]": 27,
|
63 |
+
"[=N]": 105,
|
64 |
+
"[=O+1]": 96,
|
65 |
+
"[=O]": 30,
|
66 |
+
"[=P+1]": 98,
|
67 |
+
"[=P@@H1]": 32,
|
68 |
+
"[=P@@]": 53,
|
69 |
+
"[=P@H1]": 147,
|
70 |
+
"[=P@]": 157,
|
71 |
+
"[=PH1]": 132,
|
72 |
+
"[=P]": 86,
|
73 |
+
"[=Ring1]": 163,
|
74 |
+
"[=Ring2]": 52,
|
75 |
+
"[=S+1]": 133,
|
76 |
+
"[=S@+1]": 167,
|
77 |
+
"[=S@@+1]": 42,
|
78 |
+
"[=S@@H1]": 106,
|
79 |
+
"[=S@@]": 5,
|
80 |
+
"[=S@]": 44,
|
81 |
+
"[=SH1]": 117,
|
82 |
+
"[=S]": 73,
|
83 |
+
"[B-1]": 122,
|
84 |
+
"[B@-1]": 179,
|
85 |
+
"[B@@-1]": 17,
|
86 |
+
"[B@@H1-1]": 56,
|
87 |
+
"[B@H1-1]": 121,
|
88 |
+
"[BH1-1]": 54,
|
89 |
+
"[BH2-1]": 91,
|
90 |
+
"[BH3-1]": 75,
|
91 |
+
"[B]": 108,
|
92 |
+
"[Br+1]": 166,
|
93 |
+
"[Br]": 62,
|
94 |
+
"[Branch1]": 104,
|
95 |
+
"[Branch2]": 140,
|
96 |
+
"[C+1]": 65,
|
97 |
+
"[C-1]": 8,
|
98 |
+
"[C@@H1]": 15,
|
99 |
+
"[C@@]": 173,
|
100 |
+
"[C@H1]": 29,
|
101 |
+
"[C@]": 9,
|
102 |
+
"[CH0]": 28,
|
103 |
+
"[CH1+1]": 41,
|
104 |
+
"[CH1-1]": 4,
|
105 |
+
"[CH1]": 115,
|
106 |
+
"[CH2-1]": 110,
|
107 |
+
"[CH2]": 146,
|
108 |
+
"[C]": 139,
|
109 |
+
"[Cl]": 11,
|
110 |
+
"[F+1]": 50,
|
111 |
+
"[F]": 66,
|
112 |
+
"[I]": 63,
|
113 |
+
"[N+1]": 150,
|
114 |
+
"[N-1]": 84,
|
115 |
+
"[N@+1]": 111,
|
116 |
+
"[N@@+1]": 131,
|
117 |
+
"[N@@H1+1]": 162,
|
118 |
+
"[NH0]": 148,
|
119 |
+
"[NH1]": 130,
|
120 |
+
"[N]": 19,
|
121 |
+
"[O+1]": 85,
|
122 |
+
"[O-1]": 58,
|
123 |
+
"[OH0]": 71,
|
124 |
+
"[O]": 20,
|
125 |
+
"[P+1]": 82,
|
126 |
+
"[P@+1]": 158,
|
127 |
+
"[P@@+1]": 94,
|
128 |
+
"[P@@H1]": 170,
|
129 |
+
"[P@@]": 59,
|
130 |
+
"[P@H1]": 81,
|
131 |
+
"[P@]": 175,
|
132 |
+
"[PH1]": 134,
|
133 |
+
"[PH2]": 51,
|
134 |
+
"[P]": 80,
|
135 |
+
"[Ring1]": 70,
|
136 |
+
"[Ring2]": 90,
|
137 |
+
"[S+1]": 61,
|
138 |
+
"[S@+1]": 72,
|
139 |
+
"[S@@+1]": 57,
|
140 |
+
"[S@@H1]": 45,
|
141 |
+
"[S@@]": 154,
|
142 |
+
"[S@]": 93,
|
143 |
+
"[SH0]": 182,
|
144 |
+
"[SH1]": 123,
|
145 |
+
"[SH2]": 101,
|
146 |
+
"[SH3]": 102,
|
147 |
+
"[S]": 60,
|
148 |
+
"[Si]": 119,
|
149 |
+
"[Sn+2]": 183,
|
150 |
+
"[Sn+3]": 135,
|
151 |
+
"[SnH1]": 109,
|
152 |
+
"[SnH2]": 99,
|
153 |
+
"[Sn]": 114,
|
154 |
+
"[\\123I]": 89,
|
155 |
+
"[\\B-1]": 64,
|
156 |
+
"[\\B]": 159,
|
157 |
+
"[\\Br]": 142,
|
158 |
+
"[\\C-1]": 127,
|
159 |
+
"[\\C@@H1]": 22,
|
160 |
+
"[\\C@@]": 46,
|
161 |
+
"[\\C@H1]": 49,
|
162 |
+
"[\\C@]": 145,
|
163 |
+
"[\\CH0]": 176,
|
164 |
+
"[\\CH1-1]": 153,
|
165 |
+
"[\\C]": 43,
|
166 |
+
"[\\Cl]": 37,
|
167 |
+
"[\\F]": 26,
|
168 |
+
"[\\I]": 172,
|
169 |
+
"[\\N+1]": 92,
|
170 |
+
"[\\NH1]": 103,
|
171 |
+
"[\\N]": 138,
|
172 |
+
"[\\O-1]": 141,
|
173 |
+
"[\\O]": 18,
|
174 |
+
"[\\P@@]": 113,
|
175 |
+
"[\\P]": 74,
|
176 |
+
"[\\S+1]": 95,
|
177 |
+
"[\\S@@+1]": 169,
|
178 |
+
"[\\S@@]": 180,
|
179 |
+
"[\\S@]": 116,
|
180 |
+
"[\\SH1]": 151,
|
181 |
+
"[\\S]": 48,
|
182 |
+
"[\\Si]": 168
|
183 |
+
}
|
config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_dropout": 0.0,
|
3 |
+
"activation_function": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"BartForConditionalGeneration"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"classifier_dropout": 0.0,
|
10 |
+
"d_model": 1024,
|
11 |
+
"decoder_attention_heads": 16,
|
12 |
+
"decoder_ffn_dim": 4096,
|
13 |
+
"decoder_layerdrop": 0.0,
|
14 |
+
"decoder_layers": 12,
|
15 |
+
"decoder_start_token_id": 2,
|
16 |
+
"dropout": 0.1,
|
17 |
+
"encoder_attention_heads": 16,
|
18 |
+
"encoder_ffn_dim": 4096,
|
19 |
+
"encoder_layerdrop": 0.0,
|
20 |
+
"encoder_layers": 12,
|
21 |
+
"eos_token_id": 2,
|
22 |
+
"forced_eos_token_id": 2,
|
23 |
+
"id2label": {
|
24 |
+
"0": "LABEL_0",
|
25 |
+
"1": "LABEL_1",
|
26 |
+
"2": "LABEL_2"
|
27 |
+
},
|
28 |
+
"init_std": 0.02,
|
29 |
+
"is_encoder_decoder": true,
|
30 |
+
"label2id": {
|
31 |
+
"LABEL_0": 0,
|
32 |
+
"LABEL_1": 1,
|
33 |
+
"LABEL_2": 2
|
34 |
+
},
|
35 |
+
"max_position_embeddings": 1024,
|
36 |
+
"model_type": "bart",
|
37 |
+
"num_hidden_layers": 12,
|
38 |
+
"pad_token_id": 1,
|
39 |
+
"scale_embedding": false,
|
40 |
+
"torch_dtype": "float32",
|
41 |
+
"transformers_version": "4.21.2",
|
42 |
+
"use_cache": true,
|
43 |
+
"vocab_size": 185
|
44 |
+
}
|
merges.txt
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
#version: 0.2
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db03cd3cd6a8c8ca3becf82f5ea15c2e37027cf829bb4b4580d2766df12a168a
|
3 |
+
size 1420206221
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": {
|
4 |
+
"__type": "AddedToken",
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false
|
10 |
+
},
|
11 |
+
"cls_token": {
|
12 |
+
"__type": "AddedToken",
|
13 |
+
"content": "<s>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false
|
18 |
+
},
|
19 |
+
"eos_token": {
|
20 |
+
"__type": "AddedToken",
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false
|
26 |
+
},
|
27 |
+
"errors": "replace",
|
28 |
+
"mask_token": {
|
29 |
+
"__type": "AddedToken",
|
30 |
+
"content": "<mask>",
|
31 |
+
"lstrip": true,
|
32 |
+
"normalized": true,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false
|
35 |
+
},
|
36 |
+
"model_max_length": 1024,
|
37 |
+
"name_or_path": "facebook/bart-base",
|
38 |
+
"pad_token": {
|
39 |
+
"__type": "AddedToken",
|
40 |
+
"content": "<pad>",
|
41 |
+
"lstrip": false,
|
42 |
+
"normalized": true,
|
43 |
+
"rstrip": false,
|
44 |
+
"single_word": false
|
45 |
+
},
|
46 |
+
"sep_token": {
|
47 |
+
"__type": "AddedToken",
|
48 |
+
"content": "</s>",
|
49 |
+
"lstrip": false,
|
50 |
+
"normalized": true,
|
51 |
+
"rstrip": false,
|
52 |
+
"single_word": false
|
53 |
+
},
|
54 |
+
"special_tokens_map_file": null,
|
55 |
+
"tokenizer_class": "BartTokenizer",
|
56 |
+
"unk_token": {
|
57 |
+
"__type": "AddedToken",
|
58 |
+
"content": "<unk>",
|
59 |
+
"lstrip": false,
|
60 |
+
"normalized": true,
|
61 |
+
"rstrip": false,
|
62 |
+
"single_word": false
|
63 |
+
}
|
64 |
+
}
|
vocab.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 2,
|
3 |
+
"<pad>": 1,
|
4 |
+
"<s>": 0,
|
5 |
+
"<unk>": 3
|
6 |
+
}
|