Skip to content
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

Follow HF_ENDPOINT environment variable #2905

Merged
merged 1 commit into from
Mar 20, 2024
Merged

Follow HF_ENDPOINT environment variable #2905

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
6 changes: 4 additions & 2 deletions data/belle_multiturn/belle_multiturn.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,8 @@
import os
import json
import datasets

_HF_ENDPOINT = os.getenv("HF_ENDPOINT", "https://huggingface.co")

_DESCRIPTION = "BELLE multiturn chat dataset."

Expand All @@ -13,9 +15,9 @@
}
"""

_HOMEPAGE = "https://huggingface.co/datasets/BelleGroup/multiturn_chat_0.8M"
_HOMEPAGE = f"{_HF_ENDPOINT}/datasets/BelleGroup/multiturn_chat_0.8M"
_LICENSE = "gpl-3.0"
_URL = "https://huggingface.co/datasets/BelleGroup/multiturn_chat_0.8M/resolve/main/multiturn_chat_0.8M.json"
_URL = f"{_HF_ENDPOINT}/datasets/BelleGroup/multiturn_chat_0.8M/resolve/main/multiturn_chat_0.8M.json"


class BelleMultiturn(datasets.GeneratorBasedBuilder):
Expand Down
8 changes: 6 additions & 2 deletions data/hh_rlhf_en/hh_rlhf_en.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,13 +1,17 @@
import os
import json
import datasets
from typing import List

_HF_ENDPOINT = os.getenv("_HF_ENDPOINT", "https://huggingface.co")

_DESCRIPTION = "Human preference data about helpfulness and harmlessness."

_CITATION = ""
_HOMEPAGE = "https://huggingface.co/datasets/Anthropic/hh-rlhf"

_HOMEPAGE = f"{_HF_ENDPOINT}/datasets/Anthropic/hh-rlhf"
_LICENSE = "mit"
_URL = "https://huggingface.co/datasets/Anthropic/hh-rlhf/resolve/main/"
_URL = f"{_HF_ENDPOINT}/datasets/Anthropic/hh-rlhf/resolve/main/"
_URLS = {
"train": [
_URL + "harmless-base/train.jsonl.gz",
Expand Down
8 changes: 5 additions & 3 deletions data/ultra_chat/ultra_chat.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,9 @@
import os
import json
import datasets
from typing import List

_HF_ENDPOINT = os.getenv("_HF_ENDPOINT", "https://huggingface.co")

_DESCRIPTION = "UltraChat: Large-scale, Informative, and Diverse Multi-round Dialogue Data."

Expand All @@ -16,9 +18,9 @@
}
"""

_HOMEPAGE = "https://huggingface.co/datasets/stingning/ultrachat"
_HOMEPAGE = f"{_HF_ENDPOINT}/datasets/stingning/ultrachat"
_LICENSE = "cc-by-nc-4.0"
_BASE_DATA_URL = "https://huggingface.co/datasets/stingning/ultrachat/resolve/main/train_{idx}.jsonl"
_BASE_DATA_URL = "{_HF_ENDPOINT}/datasets/stingning/ultrachat/resolve/main/train_{idx}.jsonl"


class UltraChat(datasets.GeneratorBasedBuilder):
Expand All @@ -38,7 +40,7 @@ def _info(self):
)

def _split_generators(self, dl_manager: datasets.DownloadManager):
file_paths = [dl_manager.download(_BASE_DATA_URL.format(idx=idx)) for idx in range(10)] # multiple shards
file_paths = [dl_manager.download(_BASE_DATA_URL.format(_HF_ENDPOINT=_HF_ENDPOINT,idx=idx)) for idx in range(10)] # multiple shards
return [
datasets.SplitGenerator(
name=datasets.Split.TRAIN,
Expand Down