Upload 6 files

Browse files

Files changed (6) hide show

added_tokens.json +183 -0
config.json +44 -0
merges.txt +0 -0
special_tokens_map.json +51 -0
tokenizer_config.json +64 -0
vocab.json +6 -0

added_tokens.json ADDED Viewed

	@@ -0,0 +1,183 @@

+{
+  "<mask>": 184,
+  "[#Branch1]": 12,
+  "[#Branch2]": 178,
+  "[#C-1]": 181,
+  "[#C]": 165,
+  "[#N+1]": 120,
+  "[#N]": 23,
+  "[#P]": 87,
+  "[#Ring1]": 128,
+  "[#S]": 40,
+  "[-/Ring1]": 129,
+  "[-/Ring2]": 156,
+  "[-\\Ring1]": 164,
+  "[-\\Ring2]": 34,
+  "[/123I]": 7,
+  "[/B]": 125,
+  "[/Br]": 149,
+  "[/C-1]": 68,
+  "[/C@@H1]": 13,
+  "[/C@@]": 14,
+  "[/C@H1]": 177,
+  "[/C@]": 31,
+  "[/CH0]": 126,
+  "[/CH1-1]": 88,
+  "[/CH1]": 10,
+  "[/C]": 118,
+  "[/Cl]": 155,
+  "[/F]": 6,
+  "[/I]": 83,
+  "[/N+1]": 152,
+  "[/NH0]": 55,
+  "[/NH1]": 24,
+  "[/N]": 67,
+  "[/O-1]": 171,
+  "[/OH0]": 174,
+  "[/O]": 69,
+  "[/P@@]": 16,
+  "[/P]": 79,
+  "[/S+1]": 47,
+  "[/S@@+1]": 21,
+  "[/S@@]": 160,
+  "[/S@]": 77,
+  "[/S]": 112,
+  "[/Si]": 38,
+  "[11CH3]": 107,
+  "[123I]": 124,
+  "[124I]": 136,
+  "[125I]": 39,
+  "[127I]": 36,
+  "[17F]": 143,
+  "[18F]": 97,
+  "[18OH1]": 76,
+  "[3H]": 137,
+  "[=B]": 25,
+  "[=Branch1]": 33,
+  "[=Branch2]": 100,
+  "[=CH0]": 78,
+  "[=C]": 35,
+  "[=N+1]": 144,
+  "[=N-1]": 161,
+  "[=NH0]": 27,
+  "[=N]": 105,
+  "[=O+1]": 96,
+  "[=O]": 30,
+  "[=P+1]": 98,
+  "[=P@@H1]": 32,
+  "[=P@@]": 53,
+  "[=P@H1]": 147,
+  "[=P@]": 157,
+  "[=PH1]": 132,
+  "[=P]": 86,
+  "[=Ring1]": 163,
+  "[=Ring2]": 52,
+  "[=S+1]": 133,
+  "[=S@+1]": 167,
+  "[=S@@+1]": 42,
+  "[=S@@H1]": 106,
+  "[=S@@]": 5,
+  "[=S@]": 44,
+  "[=SH1]": 117,
+  "[=S]": 73,
+  "[B-1]": 122,
+  "[B@-1]": 179,
+  "[B@@-1]": 17,
+  "[B@@H1-1]": 56,
+  "[B@H1-1]": 121,
+  "[BH1-1]": 54,
+  "[BH2-1]": 91,
+  "[BH3-1]": 75,
+  "[B]": 108,
+  "[Br+1]": 166,
+  "[Br]": 62,
+  "[Branch1]": 104,
+  "[Branch2]": 140,
+  "[C+1]": 65,
+  "[C-1]": 8,
+  "[C@@H1]": 15,
+  "[C@@]": 173,
+  "[C@H1]": 29,
+  "[C@]": 9,
+  "[CH0]": 28,
+  "[CH1+1]": 41,
+  "[CH1-1]": 4,
+  "[CH1]": 115,
+  "[CH2-1]": 110,
+  "[CH2]": 146,
+  "[C]": 139,
+  "[Cl]": 11,
+  "[F+1]": 50,
+  "[F]": 66,
+  "[I]": 63,
+  "[N+1]": 150,
+  "[N-1]": 84,
+  "[N@+1]": 111,
+  "[N@@+1]": 131,
+  "[N@@H1+1]": 162,
+  "[NH0]": 148,
+  "[NH1]": 130,
+  "[N]": 19,
+  "[O+1]": 85,
+  "[O-1]": 58,
+  "[OH0]": 71,
+  "[O]": 20,
+  "[P+1]": 82,
+  "[P@+1]": 158,
+  "[P@@+1]": 94,
+  "[P@@H1]": 170,
+  "[P@@]": 59,
+  "[P@H1]": 81,
+  "[P@]": 175,
+  "[PH1]": 134,
+  "[PH2]": 51,
+  "[P]": 80,
+  "[Ring1]": 70,
+  "[Ring2]": 90,
+  "[S+1]": 61,
+  "[S@+1]": 72,
+  "[S@@+1]": 57,
+  "[S@@H1]": 45,
+  "[S@@]": 154,
+  "[S@]": 93,
+  "[SH0]": 182,
+  "[SH1]": 123,
+  "[SH2]": 101,
+  "[SH3]": 102,
+  "[S]": 60,
+  "[Si]": 119,
+  "[Sn+2]": 183,
+  "[Sn+3]": 135,
+  "[SnH1]": 109,
+  "[SnH2]": 99,
+  "[Sn]": 114,
+  "[\\123I]": 89,
+  "[\\B-1]": 64,
+  "[\\B]": 159,
+  "[\\Br]": 142,
+  "[\\C-1]": 127,
+  "[\\C@@H1]": 22,
+  "[\\C@@]": 46,
+  "[\\C@H1]": 49,
+  "[\\C@]": 145,
+  "[\\CH0]": 176,
+  "[\\CH1-1]": 153,
+  "[\\C]": 43,
+  "[\\Cl]": 37,
+  "[\\F]": 26,
+  "[\\I]": 172,
+  "[\\N+1]": 92,
+  "[\\NH1]": 103,
+  "[\\N]": 138,
+  "[\\O-1]": 141,
+  "[\\O]": 18,
+  "[\\P@@]": 113,
+  "[\\P]": 74,
+  "[\\S+1]": 95,
+  "[\\S@@+1]": 169,
+  "[\\S@@]": 180,
+  "[\\S@]": 116,
+  "[\\SH1]": 151,
+  "[\\S]": 48,
+  "[\\Si]": 168
+}

config.json ADDED Viewed

	@@ -0,0 +1,44 @@

+{
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_position_embeddings": 1024,
+  "model_type": "bart",
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.21.2",
+  "use_cache": true,
+  "vocab_size": 185
+}

merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,51 @@

+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,64 @@

+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1024,
+  "name_or_path": "facebook/bart-base",
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "special_tokens_map_file": null,
+  "tokenizer_class": "BartTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

vocab.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "</s>": 2,
+  "<pad>": 1,
+  "<s>": 0,
+  "<unk>": 3
+}