Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,41 @@
|
|
1 |
---
|
|
|
|
|
2 |
license: mit
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
license: mit
|
5 |
+
tags:
|
6 |
+
- chemistry
|
7 |
+
- SMILES
|
8 |
+
- retrosynthesis
|
9 |
+
datasets:
|
10 |
+
- ORD
|
11 |
+
metrics:
|
12 |
+
- accuracy
|
13 |
---
|
14 |
+
# ⚠️This is an old version of [ReactionT5v2-retrosynthesis](https://huggingface.co/sagawa/ReactionT5v2-retrosynthesis). Prediction accuracy is worse.⚠️
|
15 |
+
|
16 |
+
|
17 |
+
# Model Card for ReactionT5v1-retrosynthesis
|
18 |
+
|
19 |
+
This is a ReactionT5 pre-trained to predict the reactants of reactions.
|
20 |
+
|
21 |
+
### Model Sources
|
22 |
+
|
23 |
+
<!-- Provide the basic links for the model. -->
|
24 |
+
|
25 |
+
- **Repository:** https://github.com/sagawatatsuya/ReactionT5
|
26 |
+
- **Paper:** https://arxiv.org/abs/2311.06708
|
27 |
+
|
28 |
+
## Citation
|
29 |
+
|
30 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
31 |
+
arxiv link: https://arxiv.org/abs/2311.06708
|
32 |
+
```
|
33 |
+
@misc{sagawa2023reactiont5,
|
34 |
+
title={ReactionT5: a large-scale pre-trained model towards application of limited reaction data},
|
35 |
+
author={Tatsuya Sagawa and Ryosuke Kojima},
|
36 |
+
year={2023},
|
37 |
+
eprint={2311.06708},
|
38 |
+
archivePrefix={arXiv},
|
39 |
+
primaryClass={physics.chem-ph}
|
40 |
+
}
|
41 |
+
```
|