初始化项目，由ModelHub XC社区提供模型

Model: ddidacus/smolgen-pubchem-46M-base
Source: Original Platform

tokenizer.json

@@ -0,0 +1,88 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 33,
+      "content": "[PAD]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 34,
+      "content": "[EOS]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 35,
+      "content": "[BOS]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "Split",
+    "pattern": {
+      "Regex": "(\\[[^\\]]+]|Br?|Cl?|N|O|S|P|F|I|b|c|n|o|s|p|\\(|\\)|\\.|=|#|\\+|\\/|:|@|\\?|>|\\*|\\$|%[0-9]{2}|[0-9])"
+    },
+    "behavior": "Isolated",
+    "invert": false
+  },
+  "post_processor": null,
+  "decoder": {
+    "type": "Fuse"
+  },
+  "model": {
+    "type": "WordPiece",
+    "unk_token": "[UNK]",
+    "continuing_subword_prefix": "##",
+    "max_input_chars_per_word": 100,
+    "vocab": {
+      "#": 0,
+      "=": 1,
+      "-": 2,
+      "(": 3,
+      ")": 4,
+      "1": 5,
+      "2": 6,
+      "3": 7,
+      "4": 8,
+      "5": 9,
+      "6": 10,
+      "7": 11,
+      "8": 12,
+      "9": 13,
+      "%10": 14,
+      "Br": 15,
+      "C": 16,
+      "Cl": 17,
+      "F": 18,
+      "N": 19,
+      "O": 20,
+      "S": 21,
+      "[N+]": 22,
+      "[N-]": 23,
+      "[O-]": 24,
+      "[S+]": 25,
+      "[n+]": 26,
+      "[nH]": 27,
+      "c": 28,
+      "n": 29,
+      "o": 30,
+      "s": 31,
+      "[UNK]": 32
+    }
+  }
+}