Remove private MolCrawl-HFuploader URL from dataset references
Browse files
README.md
CHANGED
|
@@ -15,10 +15,6 @@ GPT-2 medium (345M parameters) foundation model pre-trained on compound SMILES s
|
|
| 15 |
|
| 16 |
The tokenizer is a character-level BPE tokenizer (vocab_size=612) that encodes each SMILES character as a separate token. Input SMILES strings should be passed **without** spaces (e.g. `CC(=O)O`). The `[SEP]` token (id=13) is used as the end-of-sequence marker.
|
| 17 |
|
| 18 |
-
## Datasets
|
| 19 |
-
|
| 20 |
-
- **MolCrawl compounds corpus (chembl + zinc + opv + reddb + pubchemqc)**: [https://github.com/mmai-framework-lab/MolCrawl-HFuploader/blob/main/workflows/hugging_face/run_upload_hf.sh](https://github.com/mmai-framework-lab/MolCrawl-HFuploader/blob/main/workflows/hugging_face/run_upload_hf.sh) (Pre-training corpus)
|
| 21 |
-
|
| 22 |
- **Model Type**: bert
|
| 23 |
- **Data Type**: Molecule/Compound
|
| 24 |
- **Training Date**: 2026-04-24
|
|
|
|
| 15 |
|
| 16 |
The tokenizer is a character-level BPE tokenizer (vocab_size=612) that encodes each SMILES character as a separate token. Input SMILES strings should be passed **without** spaces (e.g. `CC(=O)O`). The `[SEP]` token (id=13) is used as the end-of-sequence marker.
|
| 17 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
- **Model Type**: bert
|
| 19 |
- **Data Type**: Molecule/Compound
|
| 20 |
- **Training Date**: 2026-04-24
|