add dpo mix dataset
Former-commit-id: 6def3f8bfa51b2d9d73af112352ce07db972e4c9
This commit is contained in:
@@ -1,8 +1,10 @@
|
||||
import os
|
||||
import json
|
||||
import datasets
|
||||
import os
|
||||
from typing import List
|
||||
|
||||
import datasets
|
||||
|
||||
|
||||
_HF_ENDPOINT = os.getenv("HF_ENDPOINT", "https://huggingface.co")
|
||||
|
||||
_DESCRIPTION = "UltraChat: Large-scale, Informative, and Diverse Multi-round Dialogue Data."
|
||||
@@ -24,31 +26,19 @@ _BASE_DATA_URL = "{}/datasets/stingning/ultrachat/resolve/main/train_{{idx}}.jso
|
||||
|
||||
|
||||
class UltraChat(datasets.GeneratorBasedBuilder):
|
||||
|
||||
VERSION = datasets.Version("0.0.0")
|
||||
|
||||
def _info(self):
|
||||
features = datasets.Features({
|
||||
"conversations": [{"from": datasets.Value("string"), "value": datasets.Value("string")}]
|
||||
})
|
||||
features = datasets.Features(
|
||||
{"conversations": [{"from": datasets.Value("string"), "value": datasets.Value("string")}]}
|
||||
)
|
||||
return datasets.DatasetInfo(
|
||||
description=_DESCRIPTION,
|
||||
features=features,
|
||||
homepage=_HOMEPAGE,
|
||||
license=_LICENSE,
|
||||
citation=_CITATION
|
||||
description=_DESCRIPTION, features=features, homepage=_HOMEPAGE, license=_LICENSE, citation=_CITATION
|
||||
)
|
||||
|
||||
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
|
||||
return [
|
||||
datasets.SplitGenerator(
|
||||
name=datasets.Split.TRAIN,
|
||||
gen_kwargs={
|
||||
"filepaths": file_paths
|
||||
}
|
||||
)
|
||||
]
|
||||
file_paths = [dl_manager.download(_BASE_DATA_URL.format(idx=idx)) for idx in range(10)] # multiple shards
|
||||
return [datasets.SplitGenerator(name=datasets.Split.TRAIN, gen_kwargs={"filepaths": file_paths})]
|
||||
|
||||
def _generate_examples(self, filepaths: List[str]):
|
||||
for filepath in filepaths:
|
||||
@@ -56,7 +46,7 @@ class UltraChat(datasets.GeneratorBasedBuilder):
|
||||
for row in f:
|
||||
try:
|
||||
data = json.loads(row)
|
||||
except:
|
||||
except Exception:
|
||||
continue
|
||||
key: int = data["id"]
|
||||
content: List[str] = data["data"]
|
||||
@@ -64,8 +54,7 @@ class UltraChat(datasets.GeneratorBasedBuilder):
|
||||
content.pop(-1)
|
||||
if len(content) < 2:
|
||||
continue
|
||||
conversations = [{
|
||||
"from": "human" if i % 2 == 0 else "gpt",
|
||||
"value": content[i]
|
||||
} for i in range(len(content))]
|
||||
conversations = [
|
||||
{"from": "human" if i % 2 == 0 else "gpt", "value": content[i]} for i in range(len(content))
|
||||
]
|
||||
yield key, {"conversations": conversations}
|
||||
|
||||
Reference in New Issue
Block a user