Update README.md
Browse files
README.md
CHANGED
|
@@ -19,6 +19,8 @@ Trained on ~2.7M valid SMILES and SELFIES built and curated from ChemBL34 (Zdraz
|
|
| 19 |
|
| 20 |
The "comb_smi.csv" dataset can be downloaded [here](https://huggingface.co/datasets/gbyuvd/bioactives-naturals-smiles-molgen).
|
| 21 |
|
|
|
|
|
|
|
| 22 |
## ⚡ Performance Highlights
|
| 23 |
|
| 24 |
#### SMILES
|
|
|
|
| 19 |
|
| 20 |
The "comb_smi.csv" dataset can be downloaded [here](https://huggingface.co/datasets/gbyuvd/bioactives-naturals-smiles-molgen).
|
| 21 |
|
| 22 |
+
A tentative technical report can be read [here](https://amachinewithorgans.wordpress.com/2025/09/27/fastchemtokenizer-a-new-approach-to-chemical-language-processing-via-statistical-info-theoretic-motif-mining/)
|
| 23 |
+
|
| 24 |
## ⚡ Performance Highlights
|
| 25 |
|
| 26 |
#### SMILES
|