Downloads · 30 days
53
3% of all-time downloads
biot5-base-mol2text
QizhiPei/biot5-base-mol2text
biot5-base-mol2text is a machine learning model from QizhiPei. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as mit.
For more information, please refer to our paper and GitHub repository.
All-time downloads
2.1K
Public
Parameters
252M
2 GB on disk
Likes
4
Public
Repo makeup
Click a slice to open those files.
.bin1 GB · 50%
At a glance
- Library
- transformers
- License
- mit
- Model type
- t5
- Access
- Public
- Created
- Oct 28, 2023
- Updated
- Feb 20, 2025
- SHA
- ba0a65b1
Datasets
Model card
From the Hugging Face model README
Example Usage
from transformers import T5Tokenizer, T5ForConditionalGeneration
tokenizer = T5Tokenizer.from_pretrained("QizhiPei/biot5-base-mol2text", model_max_length=512)
model = T5ForConditionalGeneration.from_pretrained('QizhiPei/biot5-base-mol2text')
task_definition = 'Definition: You are given a molecule SELFIES. Your job is to generate the molecule description in English that fits the molecule SELFIES.\n\n'
selfies_input = '[C][C][Branch1][C][O][C][C][=Branch1][C][=O][C][=Branch1][C][=O][O-1]'
task_input = f'Now complete the following example -\nInput: <bom>{selfies_input}<eom>\nOutput: '
model_input = task_definition + task_input
input_ids = tokenizer(model_input, return_tensors="pt").input_ids
generation_config = model.generation_config
generation_config.max_length = 512
generation_config.num_beams = 1
outputs = model.generate(input_ids, generation_config=generation_config)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
References
For more information, please refer to our paper and GitHub repository.
GitHub: BioT5
Authors: Qizhi Pei, Wei Zhang, Jinhua Zhu, Kehan Wu, Kaiyuan Gao, Lijun Wu, Yingce Xia, and Rui Yan
- Library
- transformers
- Type
- t5
- License
- mit
- Languages
- en
- Created
- Oct 28, 2023
- Updated
- Feb 20, 2025