Skip to content

Adding code alpaca datasets #2095

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

Closed
wants to merge 1 commit into from
Closed

Adding code alpaca datasets #2095

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
5 changes: 4 additions & 1 deletion torchtune/datasets/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
# LICENSE file in the root directory of this source tree.

from torchtune.datasets import multimodal
from torchtune.datasets._alpaca import alpaca_cleaned_dataset, alpaca_dataset
from torchtune.datasets._alpaca import alpaca_evol_codealpaca_v1_dataset, alpaca_code_instruction_120k_dataset, alpaca_code_20k_dataset, alpaca_cleaned_dataset, alpaca_dataset
from torchtune.datasets._chat import chat_dataset
from torchtune.datasets._cnn_dailymail import cnn_dailymail_articles_dataset
from torchtune.datasets._concat import ConcatDataset
Expand All @@ -27,6 +27,9 @@
__all__ = [
"alpaca_dataset",
"alpaca_cleaned_dataset",
"alpaca_code_20k_dataset",
"alpaca_code_instruction_120k_dataset",
"alpaca_evol_codealpaca_v1_dataset",
"grammar_dataset",
"samsum_dataset",
"stack_exchange_paired_dataset",
Expand Down
18 changes: 18 additions & 0 deletions torchtune/datasets/_alpaca.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -101,3 +101,21 @@ def alpaca_dataset(
original Alpaca dataset, `yahma/alpaca-cleaned <https://huggingface.co/datasets/yahma/alpaca-cleaned>`_.
See the dataset page and :func:`~torchtune.datasets.alpaca_dataset` for more details.
"""

alpaca_code_20k_dataset = partial(alpaca_dataset, source="sahil2801/CodeAlpaca-20k")
alpaca_code_20k_dataset.__doc__ = """
Builder for a variant of Alpaca-style datasets for code, `sahil2801/CodeAlpaca-20k <https://huggingface.co/datasets/sahil2801/CodeAlpaca-20k>`_.
See the dataset page and :func:`~torchtune.datasets.alpaca_dataset` for more details.
"""

alpaca_code_instruction_120k_dataset = partial(alpaca_dataset, source="iamtarun/code_instructions_120k_alpaca")
alpaca_code_instruction_120k_dataset.__doc__ = """
Builder for a variant of Alpaca-style datasets for code, `iamtarun/code_instructions_120k_alpaca <https://huggingface.co/datasets/iamtarun/code_instructions_120k_alpaca>`_.
See the dataset page and :func:`~torchtune.datasets.alpaca_dataset` for more details.
"""

alpaca_evol_codealpaca_v1_dataset = partial(alpaca_dataset, source="theblackcat102/evol-codealpaca-v1")
alpaca_evol_codealpaca_v1_dataset.__doc__ = """
Builder for a variant of Alpaca-style datasets for code in evol style, `theblackcat102/evol-codealpaca-v1 <https://huggingface.co/datasets/theblackcat102/evol-codealpaca-v1>`_.
See the dataset page and :func:`~torchtune.datasets.alpaca_dataset` for more details.
"""
Loading