add orca_dpo_pairs dataset

Former-commit-id: af683aacbae462a2a37d76d37df583e217664bd5

data/hh_rlhf_en/hh_rlhf_en.py

@@ -3,15 +3,12 @@ import json
 import datasets
 from typing import List
 
-_HF_ENDPOINT = os.getenv("_HF_ENDPOINT", "https://huggingface.co")
-
+_HF_ENDPOINT = os.getenv("HF_ENDPOINT", "https://huggingface.co")
 _DESCRIPTION = "Human preference data about helpfulness and harmlessness."
-
 _CITATION = ""
-
-_HOMEPAGE = f"{_HF_ENDPOINT}/datasets/Anthropic/hh-rlhf"
+_HOMEPAGE = "{}/datasets/Anthropic/hh-rlhf".format(_HF_ENDPOINT)
 _LICENSE = "mit"
-_URL = f"{_HF_ENDPOINT}/datasets/Anthropic/hh-rlhf/resolve/main/"
+_URL = "{}/datasets/Anthropic/hh-rlhf/resolve/main/".format(_HF_ENDPOINT)
 _URLS = {
     "train": [
         _URL + "harmless-base/train.jsonl.gz",