add readme

.idea/.gitignore

@@ -0,0 +1,3 @@
+# Default ignored files
+/shelf/
+/workspace.xml

.idea/inspectionProfiles/Project_Default.xml

@@ -0,0 +1,29 @@
+<component name="InspectionProjectProfileManager">
+  <profile version="1.0">
+    <option name="myName" value="Project Default" />
+    <inspection_tool class="PyPackageRequirementsInspection" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="ignoredPackages">
+        <value>
+          <list size="16">
+            <item index="0" class="java.lang.String" itemvalue="accelerate" />
+            <item index="1" class="java.lang.String" itemvalue="matplotlib" />
+            <item index="2" class="java.lang.String" itemvalue="torch-geometric" />
+            <item index="3" class="java.lang.String" itemvalue="torchinfo" />
+            <item index="4" class="java.lang.String" itemvalue="caikit" />
+            <item index="5" class="java.lang.String" itemvalue="pytorch-fast-transformers" />
+            <item index="6" class="java.lang.String" itemvalue="e3nn" />
+            <item index="7" class="java.lang.String" itemvalue="rdkit" />
+            <item index="8" class="java.lang.String" itemvalue="PyImpetus" />
+            <item index="9" class="java.lang.String" itemvalue="torch-scatter" />
+            <item index="10" class="java.lang.String" itemvalue="torch-nl" />
+            <item index="11" class="java.lang.String" itemvalue="torch-sparse" />
+            <item index="12" class="java.lang.String" itemvalue="mordred" />
+            <item index="13" class="java.lang.String" itemvalue="xgboost" />
+            <item index="14" class="java.lang.String" itemvalue="mamba-ssm" />
+            <item index="15" class="java.lang.String" itemvalue="evaluate" />
+          </list>
+        </value>
+      </option>
+    </inspection_tool>
+  </profile>
+</component>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/materials.selfies-ted.iml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/misc.xml

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.9" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/materials.selfies-ted.iml" filepath="$PROJECT_DIR$/.idea/materials.selfies-ted.iml" />
+    </modules>
+  </component>
+</project>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="" vcs="Git" />
+  </component>
+</project>

README.md

@@ -1,3 +1,87 @@
 ---
 license: apache-2.0
+library_name: transformers
+pipeline_tag: feature-extraction
+tags:
+- chemistry
 ---
+
+# selfies-ted
+
+selfies-ted is a project for encoding SMILES (Simplified Molecular Input Line Entry System) into SELFIES (SELF-referencing Embedded Strings) and generating embeddings for molecular representations.
+
+![selfies-ted](selfies-ted.png)
+## Model Architecture
+
+Configuration details
+
+Encoder and Decoder FFN dimensions: 256
+Number of attention heads: 4
+Number of encoder and decoder layers: 2
+Total number of hidden layers: 6
+Maximum position embeddings: 128
+Model dimension (d_model): 256
+
+## Pretrained Models and Training Logs
+We provide checkpoints of the selfies-ted model pre-trained on a dataset of molecules curated from PubChem. The pre-trained model shows competitive performance on molecular representation tasks. For model weights: "HuggingFace link".
+
+To install and use the pre-trained model:
+
+Download the selfies_ted_model.pkl file from the "HuggingFace link".
+Add the selfies-ted selfies_ted_model.pkl to the models/ directory. The directory structure should look like the following:
+
+```
+models/
+└── selfies_ted_model.pkl
+```
+
+## Installation
+
+To use this project, you'll need to install the required dependencies. We recommend using a virtual environment:
+
+```bash
+python -m venv venv
+source venv/bin/activate  # On Windows use `venv\Scripts\activate`
+```
+
+Install the required dependencies
+
+```
+pip install -r requirements.txt
+```
+
+
+## Usage
+
+### Import
+
+```
+import load
+```
+### Training the Model
+
+To train the model, use the train.py script:
+
+```
+python train.py -f <path_to_your_data_file>
+```
+
+
+Note: The actual usage may depend on the specific implementation in load.py. Please refer to the source code for detailed functionality.
+
+### Load the model and tokenizer
+```
+load.load("path/to/checkpoint.pkl")
+```
+### Encode SMILES strings
+```
+smiles_list = ["COC", "CCO"]
+```
+```
+embeddings = load.encode(smiles_list)
+```
+
+
+## Example Notebook
+
+Example notebook of this project is `selfies-ted-example.ipynb`.