luca0621 commited on
Commit
61ed3d6
·
verified ·
1 Parent(s): bd51fc2

Upload Egc Fragment-SFT checkpoint

Browse files
fragment-sft/README.md ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ # PolyEdit ReactionT5 SFT
2
+
3
+ full seq2seq adaptation of `sagawa/ReactionT5v2-forward` for property-conditioned polymer editing. Output mode: `fragment`.
fragment-sft/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "T5ForConditionalGeneration"
4
+ ],
5
+ "classifier_dropout": 0.0,
6
+ "d_ff": 2048,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "dtype": "bfloat16",
13
+ "eos_token_id": 1,
14
+ "eval_beams": 5,
15
+ "feed_forward_proj": "gated-gelu",
16
+ "initializer_factor": 1.0,
17
+ "is_encoder_decoder": true,
18
+ "is_gated_act": true,
19
+ "layer_norm_epsilon": 1e-06,
20
+ "max_length": null,
21
+ "model_type": "t5",
22
+ "num_decoder_layers": 12,
23
+ "num_heads": 12,
24
+ "num_layers": 12,
25
+ "output_past": true,
26
+ "pad_token_id": 0,
27
+ "relative_attention_max_distance": 128,
28
+ "relative_attention_num_buckets": 32,
29
+ "tie_word_embeddings": false,
30
+ "transformers_version": "4.57.6",
31
+ "use_cache": false,
32
+ "vocab_size": 268
33
+ }
fragment-sft/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "max_length": 150,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.57.6"
7
+ }
fragment-sft/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:686a3c99c86ca99df4861631fd8a4c513ac3da23a16049291a77f02784b7e081
3
+ size 397315624
fragment-sft/special_tokens_map.json ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>",
103
+ "REACTANT:",
104
+ "REAGENT:"
105
+ ],
106
+ "eos_token": {
107
+ "content": "</s>",
108
+ "lstrip": false,
109
+ "normalized": false,
110
+ "rstrip": false,
111
+ "single_word": false
112
+ },
113
+ "pad_token": {
114
+ "content": "<pad>",
115
+ "lstrip": false,
116
+ "normalized": false,
117
+ "rstrip": false,
118
+ "single_word": false
119
+ },
120
+ "unk_token": {
121
+ "content": "<unk>",
122
+ "lstrip": false,
123
+ "normalized": false,
124
+ "rstrip": false,
125
+ "single_word": false
126
+ }
127
+ }
fragment-sft/tokenizer.json ADDED
@@ -0,0 +1,1947 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 64,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": null,
10
+ "added_tokens": [
11
+ {
12
+ "id": 0,
13
+ "content": "<pad>",
14
+ "single_word": false,
15
+ "lstrip": false,
16
+ "rstrip": false,
17
+ "normalized": false,
18
+ "special": true
19
+ },
20
+ {
21
+ "id": 1,
22
+ "content": "</s>",
23
+ "single_word": false,
24
+ "lstrip": false,
25
+ "rstrip": false,
26
+ "normalized": false,
27
+ "special": true
28
+ },
29
+ {
30
+ "id": 2,
31
+ "content": "<unk>",
32
+ "single_word": false,
33
+ "lstrip": false,
34
+ "rstrip": false,
35
+ "normalized": false,
36
+ "special": true
37
+ },
38
+ {
39
+ "id": 36,
40
+ "content": "Cl",
41
+ "single_word": false,
42
+ "lstrip": false,
43
+ "rstrip": false,
44
+ "normalized": true,
45
+ "special": false
46
+ },
47
+ {
48
+ "id": 121,
49
+ "content": "<extra_id_0>",
50
+ "single_word": false,
51
+ "lstrip": false,
52
+ "rstrip": false,
53
+ "normalized": false,
54
+ "special": true
55
+ },
56
+ {
57
+ "id": 122,
58
+ "content": "<extra_id_1>",
59
+ "single_word": false,
60
+ "lstrip": false,
61
+ "rstrip": false,
62
+ "normalized": false,
63
+ "special": true
64
+ },
65
+ {
66
+ "id": 123,
67
+ "content": "<extra_id_2>",
68
+ "single_word": false,
69
+ "lstrip": false,
70
+ "rstrip": false,
71
+ "normalized": false,
72
+ "special": true
73
+ },
74
+ {
75
+ "id": 124,
76
+ "content": "<extra_id_3>",
77
+ "single_word": false,
78
+ "lstrip": false,
79
+ "rstrip": false,
80
+ "normalized": false,
81
+ "special": true
82
+ },
83
+ {
84
+ "id": 125,
85
+ "content": "<extra_id_4>",
86
+ "single_word": false,
87
+ "lstrip": false,
88
+ "rstrip": false,
89
+ "normalized": false,
90
+ "special": true
91
+ },
92
+ {
93
+ "id": 126,
94
+ "content": "<extra_id_5>",
95
+ "single_word": false,
96
+ "lstrip": false,
97
+ "rstrip": false,
98
+ "normalized": false,
99
+ "special": true
100
+ },
101
+ {
102
+ "id": 127,
103
+ "content": "<extra_id_6>",
104
+ "single_word": false,
105
+ "lstrip": false,
106
+ "rstrip": false,
107
+ "normalized": false,
108
+ "special": true
109
+ },
110
+ {
111
+ "id": 128,
112
+ "content": "<extra_id_7>",
113
+ "single_word": false,
114
+ "lstrip": false,
115
+ "rstrip": false,
116
+ "normalized": false,
117
+ "special": true
118
+ },
119
+ {
120
+ "id": 129,
121
+ "content": "<extra_id_8>",
122
+ "single_word": false,
123
+ "lstrip": false,
124
+ "rstrip": false,
125
+ "normalized": false,
126
+ "special": true
127
+ },
128
+ {
129
+ "id": 130,
130
+ "content": "<extra_id_9>",
131
+ "single_word": false,
132
+ "lstrip": false,
133
+ "rstrip": false,
134
+ "normalized": false,
135
+ "special": true
136
+ },
137
+ {
138
+ "id": 131,
139
+ "content": "<extra_id_10>",
140
+ "single_word": false,
141
+ "lstrip": false,
142
+ "rstrip": false,
143
+ "normalized": false,
144
+ "special": true
145
+ },
146
+ {
147
+ "id": 132,
148
+ "content": "<extra_id_11>",
149
+ "single_word": false,
150
+ "lstrip": false,
151
+ "rstrip": false,
152
+ "normalized": false,
153
+ "special": true
154
+ },
155
+ {
156
+ "id": 133,
157
+ "content": "<extra_id_12>",
158
+ "single_word": false,
159
+ "lstrip": false,
160
+ "rstrip": false,
161
+ "normalized": false,
162
+ "special": true
163
+ },
164
+ {
165
+ "id": 134,
166
+ "content": "<extra_id_13>",
167
+ "single_word": false,
168
+ "lstrip": false,
169
+ "rstrip": false,
170
+ "normalized": false,
171
+ "special": true
172
+ },
173
+ {
174
+ "id": 135,
175
+ "content": "<extra_id_14>",
176
+ "single_word": false,
177
+ "lstrip": false,
178
+ "rstrip": false,
179
+ "normalized": false,
180
+ "special": true
181
+ },
182
+ {
183
+ "id": 136,
184
+ "content": "<extra_id_15>",
185
+ "single_word": false,
186
+ "lstrip": false,
187
+ "rstrip": false,
188
+ "normalized": false,
189
+ "special": true
190
+ },
191
+ {
192
+ "id": 137,
193
+ "content": "<extra_id_16>",
194
+ "single_word": false,
195
+ "lstrip": false,
196
+ "rstrip": false,
197
+ "normalized": false,
198
+ "special": true
199
+ },
200
+ {
201
+ "id": 138,
202
+ "content": "<extra_id_17>",
203
+ "single_word": false,
204
+ "lstrip": false,
205
+ "rstrip": false,
206
+ "normalized": false,
207
+ "special": true
208
+ },
209
+ {
210
+ "id": 139,
211
+ "content": "<extra_id_18>",
212
+ "single_word": false,
213
+ "lstrip": false,
214
+ "rstrip": false,
215
+ "normalized": false,
216
+ "special": true
217
+ },
218
+ {
219
+ "id": 140,
220
+ "content": "<extra_id_19>",
221
+ "single_word": false,
222
+ "lstrip": false,
223
+ "rstrip": false,
224
+ "normalized": false,
225
+ "special": true
226
+ },
227
+ {
228
+ "id": 141,
229
+ "content": "<extra_id_20>",
230
+ "single_word": false,
231
+ "lstrip": false,
232
+ "rstrip": false,
233
+ "normalized": false,
234
+ "special": true
235
+ },
236
+ {
237
+ "id": 142,
238
+ "content": "<extra_id_21>",
239
+ "single_word": false,
240
+ "lstrip": false,
241
+ "rstrip": false,
242
+ "normalized": false,
243
+ "special": true
244
+ },
245
+ {
246
+ "id": 143,
247
+ "content": "<extra_id_22>",
248
+ "single_word": false,
249
+ "lstrip": false,
250
+ "rstrip": false,
251
+ "normalized": false,
252
+ "special": true
253
+ },
254
+ {
255
+ "id": 144,
256
+ "content": "<extra_id_23>",
257
+ "single_word": false,
258
+ "lstrip": false,
259
+ "rstrip": false,
260
+ "normalized": false,
261
+ "special": true
262
+ },
263
+ {
264
+ "id": 145,
265
+ "content": "<extra_id_24>",
266
+ "single_word": false,
267
+ "lstrip": false,
268
+ "rstrip": false,
269
+ "normalized": false,
270
+ "special": true
271
+ },
272
+ {
273
+ "id": 146,
274
+ "content": "<extra_id_25>",
275
+ "single_word": false,
276
+ "lstrip": false,
277
+ "rstrip": false,
278
+ "normalized": false,
279
+ "special": true
280
+ },
281
+ {
282
+ "id": 147,
283
+ "content": "<extra_id_26>",
284
+ "single_word": false,
285
+ "lstrip": false,
286
+ "rstrip": false,
287
+ "normalized": false,
288
+ "special": true
289
+ },
290
+ {
291
+ "id": 148,
292
+ "content": "<extra_id_27>",
293
+ "single_word": false,
294
+ "lstrip": false,
295
+ "rstrip": false,
296
+ "normalized": false,
297
+ "special": true
298
+ },
299
+ {
300
+ "id": 149,
301
+ "content": "<extra_id_28>",
302
+ "single_word": false,
303
+ "lstrip": false,
304
+ "rstrip": false,
305
+ "normalized": false,
306
+ "special": true
307
+ },
308
+ {
309
+ "id": 150,
310
+ "content": "<extra_id_29>",
311
+ "single_word": false,
312
+ "lstrip": false,
313
+ "rstrip": false,
314
+ "normalized": false,
315
+ "special": true
316
+ },
317
+ {
318
+ "id": 151,
319
+ "content": "<extra_id_30>",
320
+ "single_word": false,
321
+ "lstrip": false,
322
+ "rstrip": false,
323
+ "normalized": false,
324
+ "special": true
325
+ },
326
+ {
327
+ "id": 152,
328
+ "content": "<extra_id_31>",
329
+ "single_word": false,
330
+ "lstrip": false,
331
+ "rstrip": false,
332
+ "normalized": false,
333
+ "special": true
334
+ },
335
+ {
336
+ "id": 153,
337
+ "content": "<extra_id_32>",
338
+ "single_word": false,
339
+ "lstrip": false,
340
+ "rstrip": false,
341
+ "normalized": false,
342
+ "special": true
343
+ },
344
+ {
345
+ "id": 154,
346
+ "content": "<extra_id_33>",
347
+ "single_word": false,
348
+ "lstrip": false,
349
+ "rstrip": false,
350
+ "normalized": false,
351
+ "special": true
352
+ },
353
+ {
354
+ "id": 155,
355
+ "content": "<extra_id_34>",
356
+ "single_word": false,
357
+ "lstrip": false,
358
+ "rstrip": false,
359
+ "normalized": false,
360
+ "special": true
361
+ },
362
+ {
363
+ "id": 156,
364
+ "content": "<extra_id_35>",
365
+ "single_word": false,
366
+ "lstrip": false,
367
+ "rstrip": false,
368
+ "normalized": false,
369
+ "special": true
370
+ },
371
+ {
372
+ "id": 157,
373
+ "content": "<extra_id_36>",
374
+ "single_word": false,
375
+ "lstrip": false,
376
+ "rstrip": false,
377
+ "normalized": false,
378
+ "special": true
379
+ },
380
+ {
381
+ "id": 158,
382
+ "content": "<extra_id_37>",
383
+ "single_word": false,
384
+ "lstrip": false,
385
+ "rstrip": false,
386
+ "normalized": false,
387
+ "special": true
388
+ },
389
+ {
390
+ "id": 159,
391
+ "content": "<extra_id_38>",
392
+ "single_word": false,
393
+ "lstrip": false,
394
+ "rstrip": false,
395
+ "normalized": false,
396
+ "special": true
397
+ },
398
+ {
399
+ "id": 160,
400
+ "content": "<extra_id_39>",
401
+ "single_word": false,
402
+ "lstrip": false,
403
+ "rstrip": false,
404
+ "normalized": false,
405
+ "special": true
406
+ },
407
+ {
408
+ "id": 161,
409
+ "content": "<extra_id_40>",
410
+ "single_word": false,
411
+ "lstrip": false,
412
+ "rstrip": false,
413
+ "normalized": false,
414
+ "special": true
415
+ },
416
+ {
417
+ "id": 162,
418
+ "content": "<extra_id_41>",
419
+ "single_word": false,
420
+ "lstrip": false,
421
+ "rstrip": false,
422
+ "normalized": false,
423
+ "special": true
424
+ },
425
+ {
426
+ "id": 163,
427
+ "content": "<extra_id_42>",
428
+ "single_word": false,
429
+ "lstrip": false,
430
+ "rstrip": false,
431
+ "normalized": false,
432
+ "special": true
433
+ },
434
+ {
435
+ "id": 164,
436
+ "content": "<extra_id_43>",
437
+ "single_word": false,
438
+ "lstrip": false,
439
+ "rstrip": false,
440
+ "normalized": false,
441
+ "special": true
442
+ },
443
+ {
444
+ "id": 165,
445
+ "content": "<extra_id_44>",
446
+ "single_word": false,
447
+ "lstrip": false,
448
+ "rstrip": false,
449
+ "normalized": false,
450
+ "special": true
451
+ },
452
+ {
453
+ "id": 166,
454
+ "content": "<extra_id_45>",
455
+ "single_word": false,
456
+ "lstrip": false,
457
+ "rstrip": false,
458
+ "normalized": false,
459
+ "special": true
460
+ },
461
+ {
462
+ "id": 167,
463
+ "content": "<extra_id_46>",
464
+ "single_word": false,
465
+ "lstrip": false,
466
+ "rstrip": false,
467
+ "normalized": false,
468
+ "special": true
469
+ },
470
+ {
471
+ "id": 168,
472
+ "content": "<extra_id_47>",
473
+ "single_word": false,
474
+ "lstrip": false,
475
+ "rstrip": false,
476
+ "normalized": false,
477
+ "special": true
478
+ },
479
+ {
480
+ "id": 169,
481
+ "content": "<extra_id_48>",
482
+ "single_word": false,
483
+ "lstrip": false,
484
+ "rstrip": false,
485
+ "normalized": false,
486
+ "special": true
487
+ },
488
+ {
489
+ "id": 170,
490
+ "content": "<extra_id_49>",
491
+ "single_word": false,
492
+ "lstrip": false,
493
+ "rstrip": false,
494
+ "normalized": false,
495
+ "special": true
496
+ },
497
+ {
498
+ "id": 171,
499
+ "content": "<extra_id_50>",
500
+ "single_word": false,
501
+ "lstrip": false,
502
+ "rstrip": false,
503
+ "normalized": false,
504
+ "special": true
505
+ },
506
+ {
507
+ "id": 172,
508
+ "content": "<extra_id_51>",
509
+ "single_word": false,
510
+ "lstrip": false,
511
+ "rstrip": false,
512
+ "normalized": false,
513
+ "special": true
514
+ },
515
+ {
516
+ "id": 173,
517
+ "content": "<extra_id_52>",
518
+ "single_word": false,
519
+ "lstrip": false,
520
+ "rstrip": false,
521
+ "normalized": false,
522
+ "special": true
523
+ },
524
+ {
525
+ "id": 174,
526
+ "content": "<extra_id_53>",
527
+ "single_word": false,
528
+ "lstrip": false,
529
+ "rstrip": false,
530
+ "normalized": false,
531
+ "special": true
532
+ },
533
+ {
534
+ "id": 175,
535
+ "content": "<extra_id_54>",
536
+ "single_word": false,
537
+ "lstrip": false,
538
+ "rstrip": false,
539
+ "normalized": false,
540
+ "special": true
541
+ },
542
+ {
543
+ "id": 176,
544
+ "content": "<extra_id_55>",
545
+ "single_word": false,
546
+ "lstrip": false,
547
+ "rstrip": false,
548
+ "normalized": false,
549
+ "special": true
550
+ },
551
+ {
552
+ "id": 177,
553
+ "content": "<extra_id_56>",
554
+ "single_word": false,
555
+ "lstrip": false,
556
+ "rstrip": false,
557
+ "normalized": false,
558
+ "special": true
559
+ },
560
+ {
561
+ "id": 178,
562
+ "content": "<extra_id_57>",
563
+ "single_word": false,
564
+ "lstrip": false,
565
+ "rstrip": false,
566
+ "normalized": false,
567
+ "special": true
568
+ },
569
+ {
570
+ "id": 179,
571
+ "content": "<extra_id_58>",
572
+ "single_word": false,
573
+ "lstrip": false,
574
+ "rstrip": false,
575
+ "normalized": false,
576
+ "special": true
577
+ },
578
+ {
579
+ "id": 180,
580
+ "content": "<extra_id_59>",
581
+ "single_word": false,
582
+ "lstrip": false,
583
+ "rstrip": false,
584
+ "normalized": false,
585
+ "special": true
586
+ },
587
+ {
588
+ "id": 181,
589
+ "content": "<extra_id_60>",
590
+ "single_word": false,
591
+ "lstrip": false,
592
+ "rstrip": false,
593
+ "normalized": false,
594
+ "special": true
595
+ },
596
+ {
597
+ "id": 182,
598
+ "content": "<extra_id_61>",
599
+ "single_word": false,
600
+ "lstrip": false,
601
+ "rstrip": false,
602
+ "normalized": false,
603
+ "special": true
604
+ },
605
+ {
606
+ "id": 183,
607
+ "content": "<extra_id_62>",
608
+ "single_word": false,
609
+ "lstrip": false,
610
+ "rstrip": false,
611
+ "normalized": false,
612
+ "special": true
613
+ },
614
+ {
615
+ "id": 184,
616
+ "content": "<extra_id_63>",
617
+ "single_word": false,
618
+ "lstrip": false,
619
+ "rstrip": false,
620
+ "normalized": false,
621
+ "special": true
622
+ },
623
+ {
624
+ "id": 185,
625
+ "content": "<extra_id_64>",
626
+ "single_word": false,
627
+ "lstrip": false,
628
+ "rstrip": false,
629
+ "normalized": false,
630
+ "special": true
631
+ },
632
+ {
633
+ "id": 186,
634
+ "content": "<extra_id_65>",
635
+ "single_word": false,
636
+ "lstrip": false,
637
+ "rstrip": false,
638
+ "normalized": false,
639
+ "special": true
640
+ },
641
+ {
642
+ "id": 187,
643
+ "content": "<extra_id_66>",
644
+ "single_word": false,
645
+ "lstrip": false,
646
+ "rstrip": false,
647
+ "normalized": false,
648
+ "special": true
649
+ },
650
+ {
651
+ "id": 188,
652
+ "content": "<extra_id_67>",
653
+ "single_word": false,
654
+ "lstrip": false,
655
+ "rstrip": false,
656
+ "normalized": false,
657
+ "special": true
658
+ },
659
+ {
660
+ "id": 189,
661
+ "content": "<extra_id_68>",
662
+ "single_word": false,
663
+ "lstrip": false,
664
+ "rstrip": false,
665
+ "normalized": false,
666
+ "special": true
667
+ },
668
+ {
669
+ "id": 190,
670
+ "content": "<extra_id_69>",
671
+ "single_word": false,
672
+ "lstrip": false,
673
+ "rstrip": false,
674
+ "normalized": false,
675
+ "special": true
676
+ },
677
+ {
678
+ "id": 191,
679
+ "content": "<extra_id_70>",
680
+ "single_word": false,
681
+ "lstrip": false,
682
+ "rstrip": false,
683
+ "normalized": false,
684
+ "special": true
685
+ },
686
+ {
687
+ "id": 192,
688
+ "content": "<extra_id_71>",
689
+ "single_word": false,
690
+ "lstrip": false,
691
+ "rstrip": false,
692
+ "normalized": false,
693
+ "special": true
694
+ },
695
+ {
696
+ "id": 193,
697
+ "content": "<extra_id_72>",
698
+ "single_word": false,
699
+ "lstrip": false,
700
+ "rstrip": false,
701
+ "normalized": false,
702
+ "special": true
703
+ },
704
+ {
705
+ "id": 194,
706
+ "content": "<extra_id_73>",
707
+ "single_word": false,
708
+ "lstrip": false,
709
+ "rstrip": false,
710
+ "normalized": false,
711
+ "special": true
712
+ },
713
+ {
714
+ "id": 195,
715
+ "content": "<extra_id_74>",
716
+ "single_word": false,
717
+ "lstrip": false,
718
+ "rstrip": false,
719
+ "normalized": false,
720
+ "special": true
721
+ },
722
+ {
723
+ "id": 196,
724
+ "content": "<extra_id_75>",
725
+ "single_word": false,
726
+ "lstrip": false,
727
+ "rstrip": false,
728
+ "normalized": false,
729
+ "special": true
730
+ },
731
+ {
732
+ "id": 197,
733
+ "content": "<extra_id_76>",
734
+ "single_word": false,
735
+ "lstrip": false,
736
+ "rstrip": false,
737
+ "normalized": false,
738
+ "special": true
739
+ },
740
+ {
741
+ "id": 198,
742
+ "content": "<extra_id_77>",
743
+ "single_word": false,
744
+ "lstrip": false,
745
+ "rstrip": false,
746
+ "normalized": false,
747
+ "special": true
748
+ },
749
+ {
750
+ "id": 199,
751
+ "content": "<extra_id_78>",
752
+ "single_word": false,
753
+ "lstrip": false,
754
+ "rstrip": false,
755
+ "normalized": false,
756
+ "special": true
757
+ },
758
+ {
759
+ "id": 200,
760
+ "content": "<extra_id_79>",
761
+ "single_word": false,
762
+ "lstrip": false,
763
+ "rstrip": false,
764
+ "normalized": false,
765
+ "special": true
766
+ },
767
+ {
768
+ "id": 201,
769
+ "content": "<extra_id_80>",
770
+ "single_word": false,
771
+ "lstrip": false,
772
+ "rstrip": false,
773
+ "normalized": false,
774
+ "special": true
775
+ },
776
+ {
777
+ "id": 202,
778
+ "content": "<extra_id_81>",
779
+ "single_word": false,
780
+ "lstrip": false,
781
+ "rstrip": false,
782
+ "normalized": false,
783
+ "special": true
784
+ },
785
+ {
786
+ "id": 203,
787
+ "content": "<extra_id_82>",
788
+ "single_word": false,
789
+ "lstrip": false,
790
+ "rstrip": false,
791
+ "normalized": false,
792
+ "special": true
793
+ },
794
+ {
795
+ "id": 204,
796
+ "content": "<extra_id_83>",
797
+ "single_word": false,
798
+ "lstrip": false,
799
+ "rstrip": false,
800
+ "normalized": false,
801
+ "special": true
802
+ },
803
+ {
804
+ "id": 205,
805
+ "content": "<extra_id_84>",
806
+ "single_word": false,
807
+ "lstrip": false,
808
+ "rstrip": false,
809
+ "normalized": false,
810
+ "special": true
811
+ },
812
+ {
813
+ "id": 206,
814
+ "content": "<extra_id_85>",
815
+ "single_word": false,
816
+ "lstrip": false,
817
+ "rstrip": false,
818
+ "normalized": false,
819
+ "special": true
820
+ },
821
+ {
822
+ "id": 207,
823
+ "content": "<extra_id_86>",
824
+ "single_word": false,
825
+ "lstrip": false,
826
+ "rstrip": false,
827
+ "normalized": false,
828
+ "special": true
829
+ },
830
+ {
831
+ "id": 208,
832
+ "content": "<extra_id_87>",
833
+ "single_word": false,
834
+ "lstrip": false,
835
+ "rstrip": false,
836
+ "normalized": false,
837
+ "special": true
838
+ },
839
+ {
840
+ "id": 209,
841
+ "content": "<extra_id_88>",
842
+ "single_word": false,
843
+ "lstrip": false,
844
+ "rstrip": false,
845
+ "normalized": false,
846
+ "special": true
847
+ },
848
+ {
849
+ "id": 210,
850
+ "content": "<extra_id_89>",
851
+ "single_word": false,
852
+ "lstrip": false,
853
+ "rstrip": false,
854
+ "normalized": false,
855
+ "special": true
856
+ },
857
+ {
858
+ "id": 211,
859
+ "content": "<extra_id_90>",
860
+ "single_word": false,
861
+ "lstrip": false,
862
+ "rstrip": false,
863
+ "normalized": false,
864
+ "special": true
865
+ },
866
+ {
867
+ "id": 212,
868
+ "content": "<extra_id_91>",
869
+ "single_word": false,
870
+ "lstrip": false,
871
+ "rstrip": false,
872
+ "normalized": false,
873
+ "special": true
874
+ },
875
+ {
876
+ "id": 213,
877
+ "content": "<extra_id_92>",
878
+ "single_word": false,
879
+ "lstrip": false,
880
+ "rstrip": false,
881
+ "normalized": false,
882
+ "special": true
883
+ },
884
+ {
885
+ "id": 214,
886
+ "content": "<extra_id_93>",
887
+ "single_word": false,
888
+ "lstrip": false,
889
+ "rstrip": false,
890
+ "normalized": false,
891
+ "special": true
892
+ },
893
+ {
894
+ "id": 215,
895
+ "content": "<extra_id_94>",
896
+ "single_word": false,
897
+ "lstrip": false,
898
+ "rstrip": false,
899
+ "normalized": false,
900
+ "special": true
901
+ },
902
+ {
903
+ "id": 216,
904
+ "content": "<extra_id_95>",
905
+ "single_word": false,
906
+ "lstrip": false,
907
+ "rstrip": false,
908
+ "normalized": false,
909
+ "special": true
910
+ },
911
+ {
912
+ "id": 217,
913
+ "content": "<extra_id_96>",
914
+ "single_word": false,
915
+ "lstrip": false,
916
+ "rstrip": false,
917
+ "normalized": false,
918
+ "special": true
919
+ },
920
+ {
921
+ "id": 218,
922
+ "content": "<extra_id_97>",
923
+ "single_word": false,
924
+ "lstrip": false,
925
+ "rstrip": false,
926
+ "normalized": false,
927
+ "special": true
928
+ },
929
+ {
930
+ "id": 219,
931
+ "content": "<extra_id_98>",
932
+ "single_word": false,
933
+ "lstrip": false,
934
+ "rstrip": false,
935
+ "normalized": false,
936
+ "special": true
937
+ },
938
+ {
939
+ "id": 220,
940
+ "content": "<extra_id_99>",
941
+ "single_word": false,
942
+ "lstrip": false,
943
+ "rstrip": false,
944
+ "normalized": false,
945
+ "special": true
946
+ },
947
+ {
948
+ "id": 221,
949
+ "content": ".",
950
+ "single_word": false,
951
+ "lstrip": false,
952
+ "rstrip": false,
953
+ "normalized": true,
954
+ "special": false
955
+ },
956
+ {
957
+ "id": 222,
958
+ "content": "6",
959
+ "single_word": false,
960
+ "lstrip": false,
961
+ "rstrip": false,
962
+ "normalized": true,
963
+ "special": false
964
+ },
965
+ {
966
+ "id": 223,
967
+ "content": "7",
968
+ "single_word": false,
969
+ "lstrip": false,
970
+ "rstrip": false,
971
+ "normalized": true,
972
+ "special": false
973
+ },
974
+ {
975
+ "id": 224,
976
+ "content": "8",
977
+ "single_word": false,
978
+ "lstrip": false,
979
+ "rstrip": false,
980
+ "normalized": true,
981
+ "special": false
982
+ },
983
+ {
984
+ "id": 225,
985
+ "content": "<",
986
+ "single_word": false,
987
+ "lstrip": false,
988
+ "rstrip": false,
989
+ "normalized": true,
990
+ "special": false
991
+ },
992
+ {
993
+ "id": 226,
994
+ "content": ">",
995
+ "single_word": false,
996
+ "lstrip": false,
997
+ "rstrip": false,
998
+ "normalized": true,
999
+ "special": false
1000
+ },
1001
+ {
1002
+ "id": 227,
1003
+ "content": "Ag",
1004
+ "single_word": false,
1005
+ "lstrip": false,
1006
+ "rstrip": false,
1007
+ "normalized": true,
1008
+ "special": false
1009
+ },
1010
+ {
1011
+ "id": 228,
1012
+ "content": "Al",
1013
+ "single_word": false,
1014
+ "lstrip": false,
1015
+ "rstrip": false,
1016
+ "normalized": true,
1017
+ "special": false
1018
+ },
1019
+ {
1020
+ "id": 229,
1021
+ "content": "Ar",
1022
+ "single_word": false,
1023
+ "lstrip": false,
1024
+ "rstrip": false,
1025
+ "normalized": true,
1026
+ "special": false
1027
+ },
1028
+ {
1029
+ "id": 230,
1030
+ "content": "As",
1031
+ "single_word": false,
1032
+ "lstrip": false,
1033
+ "rstrip": false,
1034
+ "normalized": true,
1035
+ "special": false
1036
+ },
1037
+ {
1038
+ "id": 231,
1039
+ "content": "Au",
1040
+ "single_word": false,
1041
+ "lstrip": false,
1042
+ "rstrip": false,
1043
+ "normalized": true,
1044
+ "special": false
1045
+ },
1046
+ {
1047
+ "id": 232,
1048
+ "content": "Ba",
1049
+ "single_word": false,
1050
+ "lstrip": false,
1051
+ "rstrip": false,
1052
+ "normalized": true,
1053
+ "special": false
1054
+ },
1055
+ {
1056
+ "id": 233,
1057
+ "content": "Bi",
1058
+ "single_word": false,
1059
+ "lstrip": false,
1060
+ "rstrip": false,
1061
+ "normalized": true,
1062
+ "special": false
1063
+ },
1064
+ {
1065
+ "id": 234,
1066
+ "content": "Ca",
1067
+ "single_word": false,
1068
+ "lstrip": false,
1069
+ "rstrip": false,
1070
+ "normalized": true,
1071
+ "special": false
1072
+ },
1073
+ {
1074
+ "id": 235,
1075
+ "content": "Cu",
1076
+ "single_word": false,
1077
+ "lstrip": false,
1078
+ "rstrip": false,
1079
+ "normalized": true,
1080
+ "special": false
1081
+ },
1082
+ {
1083
+ "id": 236,
1084
+ "content": "Fe",
1085
+ "single_word": false,
1086
+ "lstrip": false,
1087
+ "rstrip": false,
1088
+ "normalized": true,
1089
+ "special": false
1090
+ },
1091
+ {
1092
+ "id": 237,
1093
+ "content": "Ge",
1094
+ "single_word": false,
1095
+ "lstrip": false,
1096
+ "rstrip": false,
1097
+ "normalized": true,
1098
+ "special": false
1099
+ },
1100
+ {
1101
+ "id": 238,
1102
+ "content": "Hg",
1103
+ "single_word": false,
1104
+ "lstrip": false,
1105
+ "rstrip": false,
1106
+ "normalized": true,
1107
+ "special": false
1108
+ },
1109
+ {
1110
+ "id": 239,
1111
+ "content": "K",
1112
+ "single_word": false,
1113
+ "lstrip": false,
1114
+ "rstrip": false,
1115
+ "normalized": true,
1116
+ "special": false
1117
+ },
1118
+ {
1119
+ "id": 240,
1120
+ "content": "Li",
1121
+ "single_word": false,
1122
+ "lstrip": false,
1123
+ "rstrip": false,
1124
+ "normalized": true,
1125
+ "special": false
1126
+ },
1127
+ {
1128
+ "id": 241,
1129
+ "content": "Mg",
1130
+ "single_word": false,
1131
+ "lstrip": false,
1132
+ "rstrip": false,
1133
+ "normalized": true,
1134
+ "special": false
1135
+ },
1136
+ {
1137
+ "id": 242,
1138
+ "content": "Mn",
1139
+ "single_word": false,
1140
+ "lstrip": false,
1141
+ "rstrip": false,
1142
+ "normalized": true,
1143
+ "special": false
1144
+ },
1145
+ {
1146
+ "id": 243,
1147
+ "content": "Mo",
1148
+ "single_word": false,
1149
+ "lstrip": false,
1150
+ "rstrip": false,
1151
+ "normalized": true,
1152
+ "special": false
1153
+ },
1154
+ {
1155
+ "id": 244,
1156
+ "content": "Na",
1157
+ "single_word": false,
1158
+ "lstrip": false,
1159
+ "rstrip": false,
1160
+ "normalized": true,
1161
+ "special": false
1162
+ },
1163
+ {
1164
+ "id": 245,
1165
+ "content": "Nd",
1166
+ "single_word": false,
1167
+ "lstrip": false,
1168
+ "rstrip": false,
1169
+ "normalized": true,
1170
+ "special": false
1171
+ },
1172
+ {
1173
+ "id": 246,
1174
+ "content": "Ni",
1175
+ "single_word": false,
1176
+ "lstrip": false,
1177
+ "rstrip": false,
1178
+ "normalized": true,
1179
+ "special": false
1180
+ },
1181
+ {
1182
+ "id": 247,
1183
+ "content": "P",
1184
+ "single_word": false,
1185
+ "lstrip": false,
1186
+ "rstrip": false,
1187
+ "normalized": true,
1188
+ "special": false
1189
+ },
1190
+ {
1191
+ "id": 248,
1192
+ "content": "Pb",
1193
+ "single_word": false,
1194
+ "lstrip": false,
1195
+ "rstrip": false,
1196
+ "normalized": true,
1197
+ "special": false
1198
+ },
1199
+ {
1200
+ "id": 249,
1201
+ "content": "Pd",
1202
+ "single_word": false,
1203
+ "lstrip": false,
1204
+ "rstrip": false,
1205
+ "normalized": true,
1206
+ "special": false
1207
+ },
1208
+ {
1209
+ "id": 250,
1210
+ "content": "Pt",
1211
+ "single_word": false,
1212
+ "lstrip": false,
1213
+ "rstrip": false,
1214
+ "normalized": true,
1215
+ "special": false
1216
+ },
1217
+ {
1218
+ "id": 251,
1219
+ "content": "Re",
1220
+ "single_word": false,
1221
+ "lstrip": false,
1222
+ "rstrip": false,
1223
+ "normalized": true,
1224
+ "special": false
1225
+ },
1226
+ {
1227
+ "id": 252,
1228
+ "content": "Rh",
1229
+ "single_word": false,
1230
+ "lstrip": false,
1231
+ "rstrip": false,
1232
+ "normalized": true,
1233
+ "special": false
1234
+ },
1235
+ {
1236
+ "id": 253,
1237
+ "content": "Ru",
1238
+ "single_word": false,
1239
+ "lstrip": false,
1240
+ "rstrip": false,
1241
+ "normalized": true,
1242
+ "special": false
1243
+ },
1244
+ {
1245
+ "id": 254,
1246
+ "content": "Sb",
1247
+ "single_word": false,
1248
+ "lstrip": false,
1249
+ "rstrip": false,
1250
+ "normalized": true,
1251
+ "special": false
1252
+ },
1253
+ {
1254
+ "id": 255,
1255
+ "content": "Si",
1256
+ "single_word": false,
1257
+ "lstrip": false,
1258
+ "rstrip": false,
1259
+ "normalized": true,
1260
+ "special": false
1261
+ },
1262
+ {
1263
+ "id": 256,
1264
+ "content": "Sm",
1265
+ "single_word": false,
1266
+ "lstrip": false,
1267
+ "rstrip": false,
1268
+ "normalized": true,
1269
+ "special": false
1270
+ },
1271
+ {
1272
+ "id": 257,
1273
+ "content": "Ta",
1274
+ "single_word": false,
1275
+ "lstrip": false,
1276
+ "rstrip": false,
1277
+ "normalized": true,
1278
+ "special": false
1279
+ },
1280
+ {
1281
+ "id": 258,
1282
+ "content": "Ti",
1283
+ "single_word": false,
1284
+ "lstrip": false,
1285
+ "rstrip": false,
1286
+ "normalized": true,
1287
+ "special": false
1288
+ },
1289
+ {
1290
+ "id": 259,
1291
+ "content": "Tl",
1292
+ "single_word": false,
1293
+ "lstrip": false,
1294
+ "rstrip": false,
1295
+ "normalized": true,
1296
+ "special": false
1297
+ },
1298
+ {
1299
+ "id": 260,
1300
+ "content": "W",
1301
+ "single_word": false,
1302
+ "lstrip": false,
1303
+ "rstrip": false,
1304
+ "normalized": true,
1305
+ "special": false
1306
+ },
1307
+ {
1308
+ "id": 261,
1309
+ "content": "Yb",
1310
+ "single_word": false,
1311
+ "lstrip": false,
1312
+ "rstrip": false,
1313
+ "normalized": true,
1314
+ "special": false
1315
+ },
1316
+ {
1317
+ "id": 262,
1318
+ "content": "Zn",
1319
+ "single_word": false,
1320
+ "lstrip": false,
1321
+ "rstrip": false,
1322
+ "normalized": true,
1323
+ "special": false
1324
+ },
1325
+ {
1326
+ "id": 263,
1327
+ "content": "Zr",
1328
+ "single_word": false,
1329
+ "lstrip": false,
1330
+ "rstrip": false,
1331
+ "normalized": true,
1332
+ "special": false
1333
+ },
1334
+ {
1335
+ "id": 264,
1336
+ "content": "e",
1337
+ "single_word": false,
1338
+ "lstrip": false,
1339
+ "rstrip": false,
1340
+ "normalized": true,
1341
+ "special": false
1342
+ },
1343
+ {
1344
+ "id": 265,
1345
+ "content": "p",
1346
+ "single_word": false,
1347
+ "lstrip": false,
1348
+ "rstrip": false,
1349
+ "normalized": true,
1350
+ "special": false
1351
+ },
1352
+ {
1353
+ "id": 266,
1354
+ "content": "REACTANT:",
1355
+ "single_word": false,
1356
+ "lstrip": false,
1357
+ "rstrip": false,
1358
+ "normalized": false,
1359
+ "special": true
1360
+ },
1361
+ {
1362
+ "id": 267,
1363
+ "content": "REAGENT:",
1364
+ "single_word": false,
1365
+ "lstrip": false,
1366
+ "rstrip": false,
1367
+ "normalized": false,
1368
+ "special": true
1369
+ }
1370
+ ],
1371
+ "normalizer": {
1372
+ "type": "Sequence",
1373
+ "normalizers": [
1374
+ {
1375
+ "type": "Nmt"
1376
+ },
1377
+ {
1378
+ "type": "NFKC"
1379
+ },
1380
+ {
1381
+ "type": "Replace",
1382
+ "pattern": {
1383
+ "Regex": " {2,}"
1384
+ },
1385
+ "content": " "
1386
+ }
1387
+ ]
1388
+ },
1389
+ "pre_tokenizer": {
1390
+ "type": "Sequence",
1391
+ "pretokenizers": [
1392
+ {
1393
+ "type": "Metaspace",
1394
+ "replacement": "▁",
1395
+ "prepend_scheme": "always",
1396
+ "split": true
1397
+ },
1398
+ {
1399
+ "type": "Digits",
1400
+ "individual_digits": true
1401
+ },
1402
+ {
1403
+ "type": "Punctuation",
1404
+ "behavior": "Isolated"
1405
+ }
1406
+ ]
1407
+ },
1408
+ "post_processor": {
1409
+ "type": "TemplateProcessing",
1410
+ "single": [
1411
+ {
1412
+ "Sequence": {
1413
+ "id": "A",
1414
+ "type_id": 0
1415
+ }
1416
+ },
1417
+ {
1418
+ "SpecialToken": {
1419
+ "id": "</s>",
1420
+ "type_id": 0
1421
+ }
1422
+ }
1423
+ ],
1424
+ "pair": [
1425
+ {
1426
+ "Sequence": {
1427
+ "id": "A",
1428
+ "type_id": 0
1429
+ }
1430
+ },
1431
+ {
1432
+ "Sequence": {
1433
+ "id": "B",
1434
+ "type_id": 1
1435
+ }
1436
+ }
1437
+ ],
1438
+ "special_tokens": {
1439
+ "</s>": {
1440
+ "id": "</s>",
1441
+ "ids": [
1442
+ 1
1443
+ ],
1444
+ "tokens": [
1445
+ "</s>"
1446
+ ]
1447
+ }
1448
+ }
1449
+ },
1450
+ "decoder": {
1451
+ "type": "Metaspace",
1452
+ "replacement": "▁",
1453
+ "prepend_scheme": "always",
1454
+ "split": true
1455
+ },
1456
+ "model": {
1457
+ "type": "Unigram",
1458
+ "unk_id": 2,
1459
+ "vocab": [
1460
+ [
1461
+ "<pad>",
1462
+ 0.0
1463
+ ],
1464
+ [
1465
+ "</s>",
1466
+ 0.0
1467
+ ],
1468
+ [
1469
+ "<unk>",
1470
+ 0.0
1471
+ ],
1472
+ [
1473
+ "C",
1474
+ -1.934062026530869
1475
+ ],
1476
+ [
1477
+ "c",
1478
+ -2.005135123981896
1479
+ ],
1480
+ [
1481
+ ")",
1482
+ -2.3305416341016603
1483
+ ],
1484
+ [
1485
+ "(",
1486
+ -2.3305416341016603
1487
+ ],
1488
+ [
1489
+ "1",
1490
+ -2.659489340254079
1491
+ ],
1492
+ [
1493
+ "2",
1494
+ -3.0147314517826524
1495
+ ],
1496
+ [
1497
+ "O",
1498
+ -3.1705660462226426
1499
+ ],
1500
+ [
1501
+ "]",
1502
+ -3.306692943444802
1503
+ ],
1504
+ [
1505
+ "[",
1506
+ -3.306692943444802
1507
+ ],
1508
+ [
1509
+ "N",
1510
+ -3.3379525475363145
1511
+ ],
1512
+ [
1513
+ "@",
1514
+ -3.375613737475505
1515
+ ],
1516
+ [
1517
+ "H",
1518
+ -3.3960003181228675
1519
+ ],
1520
+ [
1521
+ "=",
1522
+ -3.4342358584336026
1523
+ ],
1524
+ [
1525
+ "n",
1526
+ -3.9996436484078535
1527
+ ],
1528
+ [
1529
+ "3",
1530
+ -4.06624150723795
1531
+ ],
1532
+ [
1533
+ "+",
1534
+ -4.576587821405814
1535
+ ],
1536
+ [
1537
+ "ccc",
1538
+ -4.581329068949029
1539
+ ],
1540
+ [
1541
+ "cccc",
1542
+ -4.794168477161054
1543
+ ],
1544
+ [
1545
+ "F",
1546
+ -4.844444469349959
1547
+ ],
1548
+ [
1549
+ "▁C",
1550
+ -4.930731418706828
1551
+ ],
1552
+ [
1553
+ "-",
1554
+ -5.128151794820781
1555
+ ],
1556
+ [
1557
+ "CC",
1558
+ -5.188054847421637
1559
+ ],
1560
+ [
1561
+ "▁",
1562
+ -5.243375183264384
1563
+ ],
1564
+ [
1565
+ "▁CC",
1566
+ -5.43665410318811
1567
+ ],
1568
+ [
1569
+ "cc",
1570
+ -5.5072446210190025
1571
+ ],
1572
+ [
1573
+ "S",
1574
+ -5.607990514129369
1575
+ ],
1576
+ [
1577
+ "CCC",
1578
+ -5.610845771534942
1579
+ ],
1580
+ [
1581
+ "4",
1582
+ -5.6728058623804705
1583
+ ],
1584
+ [
1585
+ "CCN",
1586
+ -5.984229431727735
1587
+ ],
1588
+ [
1589
+ "▁CO",
1590
+ -6.136725098692515
1591
+ ],
1592
+ [
1593
+ "s",
1594
+ -6.163972117410355
1595
+ ],
1596
+ [
1597
+ "l",
1598
+ -6.244242813422005
1599
+ ],
1600
+ [
1601
+ "nc",
1602
+ -6.260369976115332
1603
+ ],
1604
+ [
1605
+ "Cl",
1606
+ -6.29041030199948
1607
+ ],
1608
+ [
1609
+ "NC",
1610
+ -6.301741325285667
1611
+ ],
1612
+ [
1613
+ "#",
1614
+ -6.475695381808137
1615
+ ],
1616
+ [
1617
+ "CCCC",
1618
+ -6.630889749196982
1619
+ ],
1620
+ [
1621
+ "Br",
1622
+ -6.708882955827546
1623
+ ],
1624
+ [
1625
+ "o",
1626
+ -6.8821690990922
1627
+ ],
1628
+ [
1629
+ "no",
1630
+ -7.085301372799254
1631
+ ],
1632
+ [
1633
+ "nn",
1634
+ -7.118314757276033
1635
+ ],
1636
+ [
1637
+ "CN",
1638
+ -7.148023077707199
1639
+ ],
1640
+ [
1641
+ "▁O",
1642
+ -7.184905330255651
1643
+ ],
1644
+ [
1645
+ "CCO",
1646
+ -7.223262672570243
1647
+ ],
1648
+ [
1649
+ "▁CN",
1650
+ -7.340957119808042
1651
+ ],
1652
+ [
1653
+ "ccs",
1654
+ -7.358439269448935
1655
+ ],
1656
+ [
1657
+ "▁CCC",
1658
+ -7.384181818093239
1659
+ ],
1660
+ [
1661
+ "OC",
1662
+ -7.401588967543117
1663
+ ],
1664
+ [
1665
+ "/",
1666
+ -7.412130091887384
1667
+ ],
1668
+ [
1669
+ "▁COC",
1670
+ -7.453342081307827
1671
+ ],
1672
+ [
1673
+ "nnc",
1674
+ -7.47808245293119
1675
+ ],
1676
+ [
1677
+ "cccn",
1678
+ -7.526117466256242
1679
+ ],
1680
+ [
1681
+ "▁CCOC",
1682
+ -7.581460400684973
1683
+ ],
1684
+ [
1685
+ "sc",
1686
+ -7.587476370908391
1687
+ ],
1688
+ [
1689
+ "cco",
1690
+ -7.601812309424911
1691
+ ],
1692
+ [
1693
+ "CCOCC",
1694
+ -7.70962259415791
1695
+ ],
1696
+ [
1697
+ "CCCN",
1698
+ -7.716050546596486
1699
+ ],
1700
+ [
1701
+ "oc",
1702
+ -7.76950331715161
1703
+ ],
1704
+ [
1705
+ "ccnc",
1706
+ -7.885377075776418
1707
+ ],
1708
+ [
1709
+ "▁CCO",
1710
+ -7.958354042052764
1711
+ ],
1712
+ [
1713
+ "cs",
1714
+ -7.963618836898841
1715
+ ],
1716
+ [
1717
+ "▁CCN",
1718
+ -7.969745690077621
1719
+ ],
1720
+ [
1721
+ "NCC",
1722
+ -7.982831223650715
1723
+ ],
1724
+ [
1725
+ "CNC",
1726
+ -8.015812540478317
1727
+ ],
1728
+ [
1729
+ "CCCO",
1730
+ -8.02283744281797
1731
+ ],
1732
+ [
1733
+ "nccn",
1734
+ -8.023781204384559
1735
+ ],
1736
+ [
1737
+ "CCCCC",
1738
+ -8.113410349713947
1739
+ ],
1740
+ [
1741
+ "csc",
1742
+ -8.123340128859317
1743
+ ],
1744
+ [
1745
+ "nnn",
1746
+ -8.16923209155111
1747
+ ],
1748
+ [
1749
+ "CO",
1750
+ -8.197076591417558
1751
+ ],
1752
+ [
1753
+ "cnc",
1754
+ -8.24948897316689
1755
+ ],
1756
+ [
1757
+ "OCC",
1758
+ -8.337244843539168
1759
+ ],
1760
+ [
1761
+ "ncc",
1762
+ -8.35350988501787
1763
+ ],
1764
+ [
1765
+ "CCNC",
1766
+ -8.374584543880331
1767
+ ],
1768
+ [
1769
+ "cnn",
1770
+ -8.379764985534148
1771
+ ],
1772
+ [
1773
+ "▁CCCC",
1774
+ -8.408946579060395
1775
+ ],
1776
+ [
1777
+ "ccn",
1778
+ -8.441316367356151
1779
+ ],
1780
+ [
1781
+ "▁CCCN",
1782
+ -8.455940453267049
1783
+ ],
1784
+ [
1785
+ "ncn",
1786
+ -8.509281787409483
1787
+ ],
1788
+ [
1789
+ "CCOC",
1790
+ -8.545791064619086
1791
+ ],
1792
+ [
1793
+ "5",
1794
+ -8.595231126796552
1795
+ ],
1796
+ [
1797
+ "OCCO",
1798
+ -8.620568633537287
1799
+ ],
1800
+ [
1801
+ "SCC",
1802
+ -8.675945846432537
1803
+ ],
1804
+ [
1805
+ "\\",
1806
+ -8.738088269693655
1807
+ ],
1808
+ [
1809
+ "▁CS",
1810
+ -8.745760398405787
1811
+ ],
1812
+ [
1813
+ "cn",
1814
+ -8.81287462848524
1815
+ ],
1816
+ [
1817
+ "CS",
1818
+ -8.852680543942768
1819
+ ],
1820
+ [
1821
+ "COC",
1822
+ -8.901532120821837
1823
+ ],
1824
+ [
1825
+ "▁CCCO",
1826
+ -8.971729419021525
1827
+ ],
1828
+ [
1829
+ "▁COCC",
1830
+ -8.986602855501445
1831
+ ],
1832
+ [
1833
+ "▁F",
1834
+ -9.08172188898926
1835
+ ],
1836
+ [
1837
+ "▁CCNC",
1838
+ -9.213239929783953
1839
+ ],
1840
+ [
1841
+ "nccc",
1842
+ -9.267617565078302
1843
+ ],
1844
+ [
1845
+ "▁CCS",
1846
+ -9.284123840101111
1847
+ ],
1848
+ [
1849
+ "▁N",
1850
+ -9.46465900903722
1851
+ ],
1852
+ [
1853
+ "▁CCCCO",
1854
+ -9.549659454320029
1855
+ ],
1856
+ [
1857
+ "NCCC",
1858
+ -9.592808545839064
1859
+ ],
1860
+ [
1861
+ "NCCN",
1862
+ -9.616093114468232
1863
+ ],
1864
+ [
1865
+ "CCS",
1866
+ -9.68568843530331
1867
+ ],
1868
+ [
1869
+ "cncc",
1870
+ -9.884757958758378
1871
+ ],
1872
+ [
1873
+ "CCCS",
1874
+ -10.07490132384844
1875
+ ],
1876
+ [
1877
+ "▁NC",
1878
+ -10.174180411834037
1879
+ ],
1880
+ [
1881
+ "▁COCCN",
1882
+ -10.182867019690027
1883
+ ],
1884
+ [
1885
+ "▁COCCO",
1886
+ -10.210382702506402
1887
+ ],
1888
+ [
1889
+ "▁COCCC",
1890
+ -10.390960567106395
1891
+ ],
1892
+ [
1893
+ "OCO",
1894
+ -10.445584736697652
1895
+ ],
1896
+ [
1897
+ "COCC",
1898
+ -10.469925833149428
1899
+ ],
1900
+ [
1901
+ "▁CCOCCN",
1902
+ -10.487938027145828
1903
+ ],
1904
+ [
1905
+ "SC",
1906
+ -10.868655865451124
1907
+ ],
1908
+ [
1909
+ "co",
1910
+ -11.175046369147724
1911
+ ],
1912
+ [
1913
+ "I",
1914
+ -11.188088269693656
1915
+ ],
1916
+ [
1917
+ "on",
1918
+ -11.199838029113598
1919
+ ],
1920
+ [
1921
+ "CCCCN",
1922
+ -11.273835881601958
1923
+ ],
1924
+ [
1925
+ "▁CCCCN",
1926
+ -11.694782342260607
1927
+ ],
1928
+ [
1929
+ "CCOCCN",
1930
+ -11.98760417613926
1931
+ ],
1932
+ [
1933
+ "r",
1934
+ -12.313357692926305
1935
+ ],
1936
+ [
1937
+ "B",
1938
+ -12.313457692926304
1939
+ ],
1940
+ [
1941
+ "CCCCO",
1942
+ -12.313457692926304
1943
+ ]
1944
+ ],
1945
+ "byte_fallback": false
1946
+ }
1947
+ }
fragment-sft/tokenizer_config.json ADDED
@@ -0,0 +1,1330 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": null,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "36": {
29
+ "content": "Cl",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "121": {
37
+ "content": "<extra_id_0>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "122": {
45
+ "content": "<extra_id_1>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "123": {
53
+ "content": "<extra_id_2>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "124": {
61
+ "content": "<extra_id_3>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "125": {
69
+ "content": "<extra_id_4>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "126": {
77
+ "content": "<extra_id_5>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "127": {
85
+ "content": "<extra_id_6>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "128": {
93
+ "content": "<extra_id_7>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "129": {
101
+ "content": "<extra_id_8>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "130": {
109
+ "content": "<extra_id_9>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "131": {
117
+ "content": "<extra_id_10>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "132": {
125
+ "content": "<extra_id_11>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "133": {
133
+ "content": "<extra_id_12>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "134": {
141
+ "content": "<extra_id_13>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "135": {
149
+ "content": "<extra_id_14>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "136": {
157
+ "content": "<extra_id_15>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "137": {
165
+ "content": "<extra_id_16>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "138": {
173
+ "content": "<extra_id_17>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "139": {
181
+ "content": "<extra_id_18>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "140": {
189
+ "content": "<extra_id_19>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "141": {
197
+ "content": "<extra_id_20>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "142": {
205
+ "content": "<extra_id_21>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "143": {
213
+ "content": "<extra_id_22>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "144": {
221
+ "content": "<extra_id_23>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "145": {
229
+ "content": "<extra_id_24>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "146": {
237
+ "content": "<extra_id_25>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "147": {
245
+ "content": "<extra_id_26>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "148": {
253
+ "content": "<extra_id_27>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "149": {
261
+ "content": "<extra_id_28>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "150": {
269
+ "content": "<extra_id_29>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "151": {
277
+ "content": "<extra_id_30>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "152": {
285
+ "content": "<extra_id_31>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "153": {
293
+ "content": "<extra_id_32>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "154": {
301
+ "content": "<extra_id_33>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "155": {
309
+ "content": "<extra_id_34>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "156": {
317
+ "content": "<extra_id_35>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "157": {
325
+ "content": "<extra_id_36>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "158": {
333
+ "content": "<extra_id_37>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "159": {
341
+ "content": "<extra_id_38>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "160": {
349
+ "content": "<extra_id_39>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "161": {
357
+ "content": "<extra_id_40>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "162": {
365
+ "content": "<extra_id_41>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "163": {
373
+ "content": "<extra_id_42>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "164": {
381
+ "content": "<extra_id_43>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "165": {
389
+ "content": "<extra_id_44>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "166": {
397
+ "content": "<extra_id_45>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "167": {
405
+ "content": "<extra_id_46>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "168": {
413
+ "content": "<extra_id_47>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "169": {
421
+ "content": "<extra_id_48>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "170": {
429
+ "content": "<extra_id_49>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "171": {
437
+ "content": "<extra_id_50>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "172": {
445
+ "content": "<extra_id_51>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "173": {
453
+ "content": "<extra_id_52>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "174": {
461
+ "content": "<extra_id_53>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "175": {
469
+ "content": "<extra_id_54>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "176": {
477
+ "content": "<extra_id_55>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "177": {
485
+ "content": "<extra_id_56>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "178": {
493
+ "content": "<extra_id_57>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "179": {
501
+ "content": "<extra_id_58>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "180": {
509
+ "content": "<extra_id_59>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "181": {
517
+ "content": "<extra_id_60>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "182": {
525
+ "content": "<extra_id_61>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "183": {
533
+ "content": "<extra_id_62>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "184": {
541
+ "content": "<extra_id_63>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "185": {
549
+ "content": "<extra_id_64>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "186": {
557
+ "content": "<extra_id_65>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "187": {
565
+ "content": "<extra_id_66>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "188": {
573
+ "content": "<extra_id_67>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "189": {
581
+ "content": "<extra_id_68>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "190": {
589
+ "content": "<extra_id_69>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "191": {
597
+ "content": "<extra_id_70>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "192": {
605
+ "content": "<extra_id_71>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "193": {
613
+ "content": "<extra_id_72>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "194": {
621
+ "content": "<extra_id_73>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "195": {
629
+ "content": "<extra_id_74>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "196": {
637
+ "content": "<extra_id_75>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "197": {
645
+ "content": "<extra_id_76>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "198": {
653
+ "content": "<extra_id_77>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "199": {
661
+ "content": "<extra_id_78>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "200": {
669
+ "content": "<extra_id_79>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "201": {
677
+ "content": "<extra_id_80>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "202": {
685
+ "content": "<extra_id_81>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "203": {
693
+ "content": "<extra_id_82>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "204": {
701
+ "content": "<extra_id_83>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "205": {
709
+ "content": "<extra_id_84>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "206": {
717
+ "content": "<extra_id_85>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "207": {
725
+ "content": "<extra_id_86>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "208": {
733
+ "content": "<extra_id_87>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "209": {
741
+ "content": "<extra_id_88>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "210": {
749
+ "content": "<extra_id_89>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "211": {
757
+ "content": "<extra_id_90>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "212": {
765
+ "content": "<extra_id_91>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "213": {
773
+ "content": "<extra_id_92>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "214": {
781
+ "content": "<extra_id_93>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "215": {
789
+ "content": "<extra_id_94>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "216": {
797
+ "content": "<extra_id_95>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "217": {
805
+ "content": "<extra_id_96>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "218": {
813
+ "content": "<extra_id_97>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "219": {
821
+ "content": "<extra_id_98>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ },
828
+ "220": {
829
+ "content": "<extra_id_99>",
830
+ "lstrip": false,
831
+ "normalized": false,
832
+ "rstrip": false,
833
+ "single_word": false,
834
+ "special": true
835
+ },
836
+ "221": {
837
+ "content": ".",
838
+ "lstrip": false,
839
+ "normalized": true,
840
+ "rstrip": false,
841
+ "single_word": false,
842
+ "special": false
843
+ },
844
+ "222": {
845
+ "content": "6",
846
+ "lstrip": false,
847
+ "normalized": true,
848
+ "rstrip": false,
849
+ "single_word": false,
850
+ "special": false
851
+ },
852
+ "223": {
853
+ "content": "7",
854
+ "lstrip": false,
855
+ "normalized": true,
856
+ "rstrip": false,
857
+ "single_word": false,
858
+ "special": false
859
+ },
860
+ "224": {
861
+ "content": "8",
862
+ "lstrip": false,
863
+ "normalized": true,
864
+ "rstrip": false,
865
+ "single_word": false,
866
+ "special": false
867
+ },
868
+ "225": {
869
+ "content": "<",
870
+ "lstrip": false,
871
+ "normalized": true,
872
+ "rstrip": false,
873
+ "single_word": false,
874
+ "special": false
875
+ },
876
+ "226": {
877
+ "content": ">",
878
+ "lstrip": false,
879
+ "normalized": true,
880
+ "rstrip": false,
881
+ "single_word": false,
882
+ "special": false
883
+ },
884
+ "227": {
885
+ "content": "Ag",
886
+ "lstrip": false,
887
+ "normalized": true,
888
+ "rstrip": false,
889
+ "single_word": false,
890
+ "special": false
891
+ },
892
+ "228": {
893
+ "content": "Al",
894
+ "lstrip": false,
895
+ "normalized": true,
896
+ "rstrip": false,
897
+ "single_word": false,
898
+ "special": false
899
+ },
900
+ "229": {
901
+ "content": "Ar",
902
+ "lstrip": false,
903
+ "normalized": true,
904
+ "rstrip": false,
905
+ "single_word": false,
906
+ "special": false
907
+ },
908
+ "230": {
909
+ "content": "As",
910
+ "lstrip": false,
911
+ "normalized": true,
912
+ "rstrip": false,
913
+ "single_word": false,
914
+ "special": false
915
+ },
916
+ "231": {
917
+ "content": "Au",
918
+ "lstrip": false,
919
+ "normalized": true,
920
+ "rstrip": false,
921
+ "single_word": false,
922
+ "special": false
923
+ },
924
+ "232": {
925
+ "content": "Ba",
926
+ "lstrip": false,
927
+ "normalized": true,
928
+ "rstrip": false,
929
+ "single_word": false,
930
+ "special": false
931
+ },
932
+ "233": {
933
+ "content": "Bi",
934
+ "lstrip": false,
935
+ "normalized": true,
936
+ "rstrip": false,
937
+ "single_word": false,
938
+ "special": false
939
+ },
940
+ "234": {
941
+ "content": "Ca",
942
+ "lstrip": false,
943
+ "normalized": true,
944
+ "rstrip": false,
945
+ "single_word": false,
946
+ "special": false
947
+ },
948
+ "235": {
949
+ "content": "Cu",
950
+ "lstrip": false,
951
+ "normalized": true,
952
+ "rstrip": false,
953
+ "single_word": false,
954
+ "special": false
955
+ },
956
+ "236": {
957
+ "content": "Fe",
958
+ "lstrip": false,
959
+ "normalized": true,
960
+ "rstrip": false,
961
+ "single_word": false,
962
+ "special": false
963
+ },
964
+ "237": {
965
+ "content": "Ge",
966
+ "lstrip": false,
967
+ "normalized": true,
968
+ "rstrip": false,
969
+ "single_word": false,
970
+ "special": false
971
+ },
972
+ "238": {
973
+ "content": "Hg",
974
+ "lstrip": false,
975
+ "normalized": true,
976
+ "rstrip": false,
977
+ "single_word": false,
978
+ "special": false
979
+ },
980
+ "239": {
981
+ "content": "K",
982
+ "lstrip": false,
983
+ "normalized": true,
984
+ "rstrip": false,
985
+ "single_word": false,
986
+ "special": false
987
+ },
988
+ "240": {
989
+ "content": "Li",
990
+ "lstrip": false,
991
+ "normalized": true,
992
+ "rstrip": false,
993
+ "single_word": false,
994
+ "special": false
995
+ },
996
+ "241": {
997
+ "content": "Mg",
998
+ "lstrip": false,
999
+ "normalized": true,
1000
+ "rstrip": false,
1001
+ "single_word": false,
1002
+ "special": false
1003
+ },
1004
+ "242": {
1005
+ "content": "Mn",
1006
+ "lstrip": false,
1007
+ "normalized": true,
1008
+ "rstrip": false,
1009
+ "single_word": false,
1010
+ "special": false
1011
+ },
1012
+ "243": {
1013
+ "content": "Mo",
1014
+ "lstrip": false,
1015
+ "normalized": true,
1016
+ "rstrip": false,
1017
+ "single_word": false,
1018
+ "special": false
1019
+ },
1020
+ "244": {
1021
+ "content": "Na",
1022
+ "lstrip": false,
1023
+ "normalized": true,
1024
+ "rstrip": false,
1025
+ "single_word": false,
1026
+ "special": false
1027
+ },
1028
+ "245": {
1029
+ "content": "Nd",
1030
+ "lstrip": false,
1031
+ "normalized": true,
1032
+ "rstrip": false,
1033
+ "single_word": false,
1034
+ "special": false
1035
+ },
1036
+ "246": {
1037
+ "content": "Ni",
1038
+ "lstrip": false,
1039
+ "normalized": true,
1040
+ "rstrip": false,
1041
+ "single_word": false,
1042
+ "special": false
1043
+ },
1044
+ "247": {
1045
+ "content": "P",
1046
+ "lstrip": false,
1047
+ "normalized": true,
1048
+ "rstrip": false,
1049
+ "single_word": false,
1050
+ "special": false
1051
+ },
1052
+ "248": {
1053
+ "content": "Pb",
1054
+ "lstrip": false,
1055
+ "normalized": true,
1056
+ "rstrip": false,
1057
+ "single_word": false,
1058
+ "special": false
1059
+ },
1060
+ "249": {
1061
+ "content": "Pd",
1062
+ "lstrip": false,
1063
+ "normalized": true,
1064
+ "rstrip": false,
1065
+ "single_word": false,
1066
+ "special": false
1067
+ },
1068
+ "250": {
1069
+ "content": "Pt",
1070
+ "lstrip": false,
1071
+ "normalized": true,
1072
+ "rstrip": false,
1073
+ "single_word": false,
1074
+ "special": false
1075
+ },
1076
+ "251": {
1077
+ "content": "Re",
1078
+ "lstrip": false,
1079
+ "normalized": true,
1080
+ "rstrip": false,
1081
+ "single_word": false,
1082
+ "special": false
1083
+ },
1084
+ "252": {
1085
+ "content": "Rh",
1086
+ "lstrip": false,
1087
+ "normalized": true,
1088
+ "rstrip": false,
1089
+ "single_word": false,
1090
+ "special": false
1091
+ },
1092
+ "253": {
1093
+ "content": "Ru",
1094
+ "lstrip": false,
1095
+ "normalized": true,
1096
+ "rstrip": false,
1097
+ "single_word": false,
1098
+ "special": false
1099
+ },
1100
+ "254": {
1101
+ "content": "Sb",
1102
+ "lstrip": false,
1103
+ "normalized": true,
1104
+ "rstrip": false,
1105
+ "single_word": false,
1106
+ "special": false
1107
+ },
1108
+ "255": {
1109
+ "content": "Si",
1110
+ "lstrip": false,
1111
+ "normalized": true,
1112
+ "rstrip": false,
1113
+ "single_word": false,
1114
+ "special": false
1115
+ },
1116
+ "256": {
1117
+ "content": "Sm",
1118
+ "lstrip": false,
1119
+ "normalized": true,
1120
+ "rstrip": false,
1121
+ "single_word": false,
1122
+ "special": false
1123
+ },
1124
+ "257": {
1125
+ "content": "Ta",
1126
+ "lstrip": false,
1127
+ "normalized": true,
1128
+ "rstrip": false,
1129
+ "single_word": false,
1130
+ "special": false
1131
+ },
1132
+ "258": {
1133
+ "content": "Ti",
1134
+ "lstrip": false,
1135
+ "normalized": true,
1136
+ "rstrip": false,
1137
+ "single_word": false,
1138
+ "special": false
1139
+ },
1140
+ "259": {
1141
+ "content": "Tl",
1142
+ "lstrip": false,
1143
+ "normalized": true,
1144
+ "rstrip": false,
1145
+ "single_word": false,
1146
+ "special": false
1147
+ },
1148
+ "260": {
1149
+ "content": "W",
1150
+ "lstrip": false,
1151
+ "normalized": true,
1152
+ "rstrip": false,
1153
+ "single_word": false,
1154
+ "special": false
1155
+ },
1156
+ "261": {
1157
+ "content": "Yb",
1158
+ "lstrip": false,
1159
+ "normalized": true,
1160
+ "rstrip": false,
1161
+ "single_word": false,
1162
+ "special": false
1163
+ },
1164
+ "262": {
1165
+ "content": "Zn",
1166
+ "lstrip": false,
1167
+ "normalized": true,
1168
+ "rstrip": false,
1169
+ "single_word": false,
1170
+ "special": false
1171
+ },
1172
+ "263": {
1173
+ "content": "Zr",
1174
+ "lstrip": false,
1175
+ "normalized": true,
1176
+ "rstrip": false,
1177
+ "single_word": false,
1178
+ "special": false
1179
+ },
1180
+ "264": {
1181
+ "content": "e",
1182
+ "lstrip": false,
1183
+ "normalized": true,
1184
+ "rstrip": false,
1185
+ "single_word": false,
1186
+ "special": false
1187
+ },
1188
+ "265": {
1189
+ "content": "p",
1190
+ "lstrip": false,
1191
+ "normalized": true,
1192
+ "rstrip": false,
1193
+ "single_word": false,
1194
+ "special": false
1195
+ },
1196
+ "266": {
1197
+ "content": "REACTANT:",
1198
+ "lstrip": false,
1199
+ "normalized": false,
1200
+ "rstrip": false,
1201
+ "single_word": false,
1202
+ "special": true
1203
+ },
1204
+ "267": {
1205
+ "content": "REAGENT:",
1206
+ "lstrip": false,
1207
+ "normalized": false,
1208
+ "rstrip": false,
1209
+ "single_word": false,
1210
+ "special": true
1211
+ }
1212
+ },
1213
+ "additional_special_tokens": [
1214
+ "<extra_id_0>",
1215
+ "<extra_id_1>",
1216
+ "<extra_id_2>",
1217
+ "<extra_id_3>",
1218
+ "<extra_id_4>",
1219
+ "<extra_id_5>",
1220
+ "<extra_id_6>",
1221
+ "<extra_id_7>",
1222
+ "<extra_id_8>",
1223
+ "<extra_id_9>",
1224
+ "<extra_id_10>",
1225
+ "<extra_id_11>",
1226
+ "<extra_id_12>",
1227
+ "<extra_id_13>",
1228
+ "<extra_id_14>",
1229
+ "<extra_id_15>",
1230
+ "<extra_id_16>",
1231
+ "<extra_id_17>",
1232
+ "<extra_id_18>",
1233
+ "<extra_id_19>",
1234
+ "<extra_id_20>",
1235
+ "<extra_id_21>",
1236
+ "<extra_id_22>",
1237
+ "<extra_id_23>",
1238
+ "<extra_id_24>",
1239
+ "<extra_id_25>",
1240
+ "<extra_id_26>",
1241
+ "<extra_id_27>",
1242
+ "<extra_id_28>",
1243
+ "<extra_id_29>",
1244
+ "<extra_id_30>",
1245
+ "<extra_id_31>",
1246
+ "<extra_id_32>",
1247
+ "<extra_id_33>",
1248
+ "<extra_id_34>",
1249
+ "<extra_id_35>",
1250
+ "<extra_id_36>",
1251
+ "<extra_id_37>",
1252
+ "<extra_id_38>",
1253
+ "<extra_id_39>",
1254
+ "<extra_id_40>",
1255
+ "<extra_id_41>",
1256
+ "<extra_id_42>",
1257
+ "<extra_id_43>",
1258
+ "<extra_id_44>",
1259
+ "<extra_id_45>",
1260
+ "<extra_id_46>",
1261
+ "<extra_id_47>",
1262
+ "<extra_id_48>",
1263
+ "<extra_id_49>",
1264
+ "<extra_id_50>",
1265
+ "<extra_id_51>",
1266
+ "<extra_id_52>",
1267
+ "<extra_id_53>",
1268
+ "<extra_id_54>",
1269
+ "<extra_id_55>",
1270
+ "<extra_id_56>",
1271
+ "<extra_id_57>",
1272
+ "<extra_id_58>",
1273
+ "<extra_id_59>",
1274
+ "<extra_id_60>",
1275
+ "<extra_id_61>",
1276
+ "<extra_id_62>",
1277
+ "<extra_id_63>",
1278
+ "<extra_id_64>",
1279
+ "<extra_id_65>",
1280
+ "<extra_id_66>",
1281
+ "<extra_id_67>",
1282
+ "<extra_id_68>",
1283
+ "<extra_id_69>",
1284
+ "<extra_id_70>",
1285
+ "<extra_id_71>",
1286
+ "<extra_id_72>",
1287
+ "<extra_id_73>",
1288
+ "<extra_id_74>",
1289
+ "<extra_id_75>",
1290
+ "<extra_id_76>",
1291
+ "<extra_id_77>",
1292
+ "<extra_id_78>",
1293
+ "<extra_id_79>",
1294
+ "<extra_id_80>",
1295
+ "<extra_id_81>",
1296
+ "<extra_id_82>",
1297
+ "<extra_id_83>",
1298
+ "<extra_id_84>",
1299
+ "<extra_id_85>",
1300
+ "<extra_id_86>",
1301
+ "<extra_id_87>",
1302
+ "<extra_id_88>",
1303
+ "<extra_id_89>",
1304
+ "<extra_id_90>",
1305
+ "<extra_id_91>",
1306
+ "<extra_id_92>",
1307
+ "<extra_id_93>",
1308
+ "<extra_id_94>",
1309
+ "<extra_id_95>",
1310
+ "<extra_id_96>",
1311
+ "<extra_id_97>",
1312
+ "<extra_id_98>",
1313
+ "<extra_id_99>",
1314
+ "REACTANT:",
1315
+ "REAGENT:"
1316
+ ],
1317
+ "clean_up_tokenization_spaces": true,
1318
+ "eos_token": "</s>",
1319
+ "extra_ids": 100,
1320
+ "extra_special_tokens": {},
1321
+ "max_length": 100,
1322
+ "model_max_length": 1000000000000000019884624838656,
1323
+ "pad_token": "<pad>",
1324
+ "return_tensors": "pt",
1325
+ "stride": 0,
1326
+ "tokenizer_class": "T5TokenizerFast",
1327
+ "truncation_side": "right",
1328
+ "truncation_strategy": "longest_first",
1329
+ "unk_token": "<unk>"
1330
+ }
fragment-sft/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f1232ee55b41fc9390cefb5c467b69c9ce03ed68a7e8c0169230d5159cbc9d4
3
+ size 5905
fragment-sft/training_meta.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model": "sagawa/ReactionT5v2-forward",
3
+ "properties": [
4
+ "Egc"
5
+ ],
6
+ "split_seed": 42,
7
+ "raw_train_examples": 15016,
8
+ "sampled_train_examples": 15016,
9
+ "validation_examples": 232,
10
+ "raw_property_counts": {
11
+ "Egc": 15016
12
+ },
13
+ "sampled_property_counts": {
14
+ "Egc": 15016
15
+ },
16
+ "method": "full",
17
+ "architecture": "seq2seq",
18
+ "output_mode": "fragment",
19
+ "input_mode": "reaction_delta",
20
+ "delta_bin_width": 0.2,
21
+ "sampling_alpha": 1.0,
22
+ "max_attachments": 2,
23
+ "test_fraction": 0.2,
24
+ "val_fraction": 0.05,
25
+ "input_max_length": 256,
26
+ "target_max_length": 64,
27
+ "tokenizer_escape_map": {
28
+ "0": "<extra_id_1>",
29
+ "9": "<extra_id_2>",
30
+ ":": "<extra_id_3>",
31
+ "*": "<extra_id_0>",
32
+ "<POLYEDIT>": "<extra_id_10>",
33
+ "<SOURCE>": "<extra_id_11>",
34
+ "</SOURCE>": "<extra_id_12>",
35
+ "<SOURCE_VALUE>": "<extra_id_13>",
36
+ "</SOURCE_VALUE>": "<extra_id_14>",
37
+ "<TARGET_LO>": "<extra_id_15>",
38
+ "</TARGET_LO>": "<extra_id_16>",
39
+ "<TARGET_HI>": "<extra_id_17>",
40
+ "</TARGET_HI>": "<extra_id_18>",
41
+ "<UP>": "<extra_id_19>",
42
+ "<DOWN>": "<extra_id_20>",
43
+ "<SAME>": "<extra_id_21>",
44
+ "<PRODUCT>": "<extra_id_22>",
45
+ "<RULE>": "<extra_id_23>",
46
+ "<PROP_Egc>": "<extra_id_24>",
47
+ "<PROP_Egb>": "<extra_id_25>",
48
+ "<PROP_Eea>": "<extra_id_26>",
49
+ "<PROP_Ei>": "<extra_id_27>",
50
+ "<PROP_EPS>": "<extra_id_28>",
51
+ "<PROP_Nc>": "<extra_id_29>",
52
+ "<PROP_Xc>": "<extra_id_30>",
53
+ "<PROP_Eat>": "<extra_id_31>"
54
+ },
55
+ "tokenizer_coverage": {
56
+ "sample_sequences": 8192,
57
+ "tokens": 175712,
58
+ "unknown": 0,
59
+ "unknown_rate": 0.0
60
+ },
61
+ "data_sha256": "622a31c09513369e2111ebb9919c58c5c2b5f2e75c878d4d27e336b339270405",
62
+ "best_metric": 0.7922660708427429,
63
+ "best_checkpoint": "artifacts/reactiont5-egc-fragment-sft/train/checkpoint-590",
64
+ "metrics": {
65
+ "train_runtime": 204.0785,
66
+ "train_samples_per_second": 367.898,
67
+ "train_steps_per_second": 2.891,
68
+ "total_flos": 4327937893859328.0,
69
+ "train_loss": 1.7349968085854741,
70
+ "epoch": 5.0,
71
+ "step": 590
72
+ }
73
+ }