Upload dataset, tokenizer, categorical_mappings

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+categorical_mappings.json filter=lfs diff=lfs merge=lfs -text
+data.csv filter=lfs diff=lfs merge=lfs -text

categorical_mappings.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:388ee9e9b7aba820df3cef46aba8e0c5c327e3a32698a19de13e19c430068361
+size 62638684

data.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d4a90496ce7239c9bc22afe88c2728b74981f37e1f93a66ee56ac9f0853f036
+size 48104596

tokenizer_smiles_diffusion.json

@@ -0,0 +1,55 @@
+{
+    "properties": {
+        "regex": "(\\[[^\\]]+]|Br?|Cl?|N|O|S|P|F|I|b|c|n|o|s|p|\\(|\\)|\\.|=|#|-|\\+|\\\\\\\\|\\/|:|~|@|\\?|>|\\*|\\$|\\%[0-9]{2}|[0-9]|.)",
+        "special_tokens": {
+            "start": "^",
+            "end": "&",
+            "pad": "<PAD>",
+            "unknown": "?",
+            "mask": "<MASK>",
+            "sep": "<SEP>"
+        },
+        "chem_start_idx": 6
+    },
+    "vocabulary": [
+        "<PAD>",
+        "?",
+        "^",
+        "&",
+        "<MASK>",
+        "<SEP>",
+        "O",
+        "=",
+        "C",
+        "1",
+        "N",
+        "(",
+        "/",
+        "c",
+        "2",
+        "n",
+        "[nH]",
+        ")",
+        "[C@H]",
+        "[C@@H]",
+        "3",
+        "Br",
+        "F",
+        "S",
+        "Cl",
+        "\\",
+        "[N+]",
+        "[O-]",
+        "#",
+        "4",
+        "s",
+        "-",
+        "o",
+        "5",
+        "[C@@]",
+        "[C@]",
+        "6",
+        "P",
+        "7"
+    ]
+}