Update README.md

README.md

@@ -1,21 +1,43 @@
 ---
 license: apache-2.0
+metrics:
+- accuracy
+pipeline_tag: feature-extraction
+tags:
+- chemistry
+- foundation models
+- AI4Science
+- materials
+- molecules
+- safetensors
+- pytorch
+- transformer
+- diffusers
+library_name: transformers
 ---
-# SMILES-based State-Space Encoder-Decoder (SMI-SSED)
+
+# SMILES-based State-Space Encoder-Decoder (SMI-SSED) - MoLMamba
 
 This repository provides PyTorch source code associated with our publication, "A Mamba-Based Foundation Model for Chemistry".
 
-**Paper:** [Arxiv Link]()
+**Paper:** [Arxiv Link](https://openreview.net/pdf?id=HTgCs0KSTl)
 
-**HuggingFace:** [HuggingFace Link](https://huggingface.co/ibm/materials.smi-ted)
+**HuggingFace:** [HuggingFace Link](https://huggingface.co/ibm/materials.smi_ssed)
 
 For more information contact: [email protected] or [email protected].
 
-![smi-ssed](https://github.com/IBM/materials/blob/main/models/smi_ssed/images/smi-ssed.png)
+![smi-ssed](https://raw.githubusercontent.com/IBM/materials/main/models/smi_ssed/images/smi-ssed.png)
 
 ## Introduction
 
-We present a large encoder-decoder chemical foundation model, SMILES-based State-Space Encoder-Decoder (SMI-SSED), pre-trained on a curated dataset of 91 million SMILES samples sourced from PubChem, equivalent to 4 billion molecular tokens. SMI-SSED supports various complex tasks, including quantum property prediction, with two main variants ($336$ and $8 \times 336M$). Our experiments across multiple benchmark datasets demonstrate state-of-the-art performance for various tasks. Model weights are available at: [HuggingFace Link](https://huggingface.co/ibm/materials.smi-ted).
+We present a Mamba-based encoder-decoder chemical foundation model, SMILES-based State-Space Encoder-Decoder (SMI-SSED), pre-trained on a curated dataset of 91 million SMILES samples sourced from PubChem, equivalent to 4 billion molecular tokens. SMI-SSED supports various complex tasks, including quantum property prediction, with two main variants ($336$ and $8 \times 336M$). Our experiments across multiple benchmark datasets demonstrate state-of-the-art performance for various tasks. 
+
+We provide the model weights in two formats:
+
+- PyTorch (`.pt`): [smi_ssed_130.pt](smi_ssed_130.pt)
+- safetensors (`.bin`): [smi_ssed_130.bin](smi_ssed_130.bin)
+
+For more information contact: [email protected] or [email protected].
 
 ## Table of Contents