ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

use pre-commit

Browse Source 
Former-commit-id: 7cfede95df22a9ff236788f04159b6b16b8d04bb
This commit is contained in:
hiyouga
2024-10-29 09:07:46 +00:00
parent 8f5921692e
commit 248d5daaff
66 changed files with 1028 additions and 1044 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
data/belle_multiturn/belle_multiturn.py
View File

@@ -17,9 +17,9 @@ _CITATION = """\
}
"""
_HOMEPAGE = "{}/datasets/BelleGroup/multiturn_chat_0.8M".format(_HF_ENDPOINT)
_HOMEPAGE = f"{_HF_ENDPOINT}/datasets/BelleGroup/multiturn_chat_0.8M"
_LICENSE = "gpl-3.0"
_URL = "{}/datasets/BelleGroup/multiturn_chat_0.8M/resolve/main/multiturn_chat_0.8M.json".format(_HF_ENDPOINT)
_URL = f"{_HF_ENDPOINT}/datasets/BelleGroup/multiturn_chat_0.8M/resolve/main/multiturn_chat_0.8M.json"
class BelleMultiturn(datasets.GeneratorBasedBuilder):
@@ -38,7 +38,7 @@ class BelleMultiturn(datasets.GeneratorBasedBuilder):
return [datasets.SplitGenerator(name=datasets.Split.TRAIN, gen_kwargs={"filepath": file_path})]
def _generate_examples(self, filepath: str):
with open(filepath, "r", encoding="utf-8") as f:
with open(filepath, encoding="utf-8") as f:
for key, row in enumerate(f):
data = json.loads(row)
conversations = []