Update README.md

README.md

@@ -1,3 +1,36 @@
----
-license: gemma
----
+---
+license: cc-by-nc-4.0
+language:
+- en
+library_name: transformers
+tags:
+- chemistry
+- biology
+---
+Chemma-2B is a continually pretrained [gemma-2b](https://huggingface.co/google/gemma-2b) model for organic molecules. 
+It is pretrained on (soon-to-be-released) 40B tokens covering 110M+ molecules from PubChem as well as their chemical properties 
+(molecular weight, synthetic accessibility score, drug-likeness etc.) 
+and similarities (Tanimoto distance between ECFP fingerprints).
+
+Example prompts:
+
+`</s>[START_SMILES]CC(=O)OC1=CC=CC=C1C(=O)O[END_SMILES][SAS]` will attempt to predict the synthetic accessibility score of the given molecule.
+
+`</s>[SAS]2.25[/SAS][SIMILAR]0.62 CC(=O)OC1=CC=CC=C1C(=O)O[/SIMILAR][START_SMILES]` will attempt to generate a molecule that has 2.25 SAS score and 
+has a 0.62 similarity score to the given molecule.
+
+The model can be wrapped into an optimization loop to traverse the chemical space with evolving prompts. 
+
+A preprint with the details of the model and an optimization algorithm built on top of this model that sets state-of-the-art on Practical Molecular Optimization 
+and other benchmarks will be released soon.
+
+Few notes:
+* All queries should start with `</s>` symbol.
+* All numbers are rounded to two decimal points.
+* All SMILES are canonicalized using `rdkit`.
+* Available tags: `[CLOGP]`, `[WEIGHT]`, `[QED]`, `[SAS]`, `[TPSA]`, `[RINGCOUNT]`, `[SIMILAR]`...
+
+The model is part of the 3-model family: [Chemlactica-125M](https://huggingface.co/yerevann/chemlactica-125m), 
+[Chemlactica-1.3B](https://huggingface.co/yerevann/chemlactica-1.3b) and [Chemma-2B](https://huggingface.co/yerevann/chemma-2b).
+
+We are looking forward to see the community using the model in new applications and contexts.