zjunlp
/

MolGen-large

Text2Text Generation

molecular language model

molecule generation

Model card Files Files and versions Community

ZJU-Fangyin commited on Feb 3, 2023

Commit

6ffb3a2

•

1 Parent(s): 3584ca4

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -16,7 +16,7 @@ With a training corpus of over 100 million molecules in SELFIES representation,
 Specifically, MolGen employs a bidirectional Transformer as its encoder and an autoregressive Transformer as its decoder.
 Through its carefully designed multi-task molecular prefix tuning (MPT), MolGen can generate molecules with desired properties, making it a valuable tool for molecular optimization.
-![image.png](./pretrain.pdf)
 ## Intended uses
 You can use the raw model for molecule generation or fine-tune it to a downstream task. Please take note that the following examples only demonstrate the utilization of our pre-trained model for molecule generation. See the [repository](https://github.com/zjunlp/MolGen) to look for fine-tune details on a task that interests you.

 Specifically, MolGen employs a bidirectional Transformer as its encoder and an autoregressive Transformer as its decoder.
 Through its carefully designed multi-task molecular prefix tuning (MPT), MolGen can generate molecules with desired properties, making it a valuable tool for molecular optimization.
+![image.png](./model.png)
 ## Intended uses
 You can use the raw model for molecule generation or fine-tune it to a downstream task. Please take note that the following examples only demonstrate the utilization of our pre-trained model for molecule generation. See the [repository](https://github.com/zjunlp/MolGen) to look for fine-tune details on a task that interests you.