Update SMILES tokenizer vocabulary, Ume tokenizers and model utilities

* Updates SMILES vocabulary with  tokenized chembl, m3-20m, geom, and zinc20 smiles in order of token count (some tokens already existed, which were added to the end of the file)

* adds Ume utilities: modalities and get_vocab
* enables to instantiate Ume without a checkpoint and adds Ume.load_from_checkpoint
* applies SMILES tokenizer vocab in the ume tokenizers
* distinguishes which reserved tokens are used (extra special tokens, reserved for amino acids, reserved for smiles...)

* removes duplicate tokenizer vocab definitions
* modifies _load_vocabularies in _ume_tokenizers.py to read from lobster/assets/smiles_tokenizer/vocab.txt and lobster/assets/latent_generator_tokenizer/vocab.txt instead and remove special tokens from these files
does not modify amino acid and nucleotide tokenizers because these do non have vocab files in the non-UME tokenizers (they're also less likely to change, so duplication is less of an issue)

Author: cgrambow

notebooks/04-ume-multimodal-embeddings.ipynb

@@ -11,15 +11,51 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/zadorozk/Desktop/code/lobster/.venv/lib/python3.12/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Supported modalities: ['SMILES', 'amino_acid', 'nucleotide', '3d_coordinates']\n",
+      "Vocab size: 1536\n"
+     ]
+    }
+   ],
    "source": [
     "from lobster.model import Ume\n",
     "\n",
-    "checkpoint = \"<your checkpoint>\"\n",
+    "ume = Ume()\n",
     "\n",
-    "ume = Ume(checkpoint, freeze=True)"
+    "print(f\"Supported modalities: {ume.modalities}\")\n",
+    "print(f\"Vocab size: {len(ume.get_vocab())}\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Load from checkpoint"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "checkpoint = \"ume-checkpoints/last.ckpt\" # Replace with the correct checkpoint path\n",
+    "\n",
+    "ume = Ume.load_from_checkpoint(checkpoint)"
    ]
   },
   {
@@ -208,8 +244,22 @@
   }
  ],
  "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
   "language_info": {
-   "name": "python"
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.9"
   }
  },
  "nbformat": 4,