Skip to content

Add LongT5 support #36

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Shivanandroy wants to merge 4 commits into
base: main
Choose a base branch
from
Open

Add LongT5 support #36

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
cdeae90
longt5
Jun 24, 2022
5df526d
Merge pull request #35 from somakaushik98/main
somakaushik98 Jun 24, 2022
4c1afee
updated transformers version
Jul 19, 2022
1e26395
Merge pull request #38 from somakaushik98/main
somakaushik98 Jul 19, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,5 +2,5 @@ numpy
pandas
sentencepiece
torch>=1.7.0,!=1.8.0
transformers==4.16.2
transformers==4.20.1
pytorch-lightning==1.5.10
9 changes: 8 additions & 1 deletion simplet5/simplet5.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,8 +8,9 @@
PreTrainedTokenizer,
T5TokenizerFast as T5Tokenizer,
MT5TokenizerFast as MT5Tokenizer,
AutoTokenizer,
LongT5ForConditionalGeneration
)
from transformers import AutoTokenizer
from torch.optim import AdamW
from torch.utils.data import Dataset, DataLoader
from transformers import AutoModelWithLMHead, AutoTokenizer
Expand Down Expand Up @@ -311,6 +312,9 @@ def from_pretrained(self, model_type="t5", model_name="t5-base") -> None:
self.model = T5ForConditionalGeneration.from_pretrained(
f"{model_name}", return_dict=True
)
elif model_type == 'longt5':
self.model = LongT5ForConditionalGeneration.from_pretrained(f"{model_name}")
self.tokenizer = AutoTokenizer.from_pretrained(f"{model_name}")

def train(
self,
Expand Down Expand Up @@ -413,6 +417,9 @@ def load_model(
elif model_type == "byt5":
self.model = T5ForConditionalGeneration.from_pretrained(f"{model_dir}")
self.tokenizer = ByT5Tokenizer.from_pretrained(f"{model_dir}")
elif model_type == 'longt5':
self.model = LongT5ForConditionalGeneration.from_pretrained(f"{model_dir}")
self.tokenizer = AutoTokenizer.from_pretrained(f"{model_dir}")

if use_gpu:
if torch.cuda.is_available():
Expand Down