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

add dpo mix dataset

Browse Source 
Former-commit-id: 6def3f8bfa51b2d9d73af112352ce07db972e4c9
This commit is contained in:
hiyouga
2024-04-20 01:31:38 +08:00
parent b3b5b530d1
commit 0cb596fee1
4 changed files with 59 additions and 105 deletions
Download Patch File Download Diff File Expand all files Collapse all files

61
data/hh_rlhf_en/hh_rlhf_en.py
View File

@@ -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 = "Human preference data about helpfulness and harmlessness."
_CITATION = ""
@@ -14,50 +16,37 @@ _URLS = {
_URL + "harmless-base/train.jsonl.gz",
_URL + "helpful-base/train.jsonl.gz",
_URL + "helpful-online/train.jsonl.gz",
_URL + "helpful-rejection-sampled/train.jsonl.gz"
_URL + "helpful-rejection-sampled/train.jsonl.gz",
],
"test": [
_URL + "harmless-base/test.jsonl.gz",
_URL + "helpful-base/test.jsonl.gz",
_URL + "helpful-online/test.jsonl.gz",
_URL + "helpful-rejection-sampled/test.jsonl.gz"
]
_URL + "helpful-rejection-sampled/test.jsonl.gz",
],
}
class HhRlhfEn(datasets.GeneratorBasedBuilder):
VERSION = datasets.Version("0.0.0")
def _info(self) -> datasets.DatasetInfo:
features = datasets.Features({
"instruction": datasets.Value("string"),
"output": datasets.Sequence(datasets.Value("string")),
"history": datasets.Sequence(datasets.Sequence(datasets.Value("string")))
})
features = datasets.Features(
{
"instruction": datasets.Value("string"),
"output": datasets.Sequence(datasets.Value("string")),
"history": datasets.Sequence(datasets.Sequence(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_path = dl_manager.download_and_extract(_URLS)
return [
datasets.SplitGenerator(
name=datasets.Split.TRAIN,
gen_kwargs={
"filepaths": file_path["train"]
}
),
datasets.SplitGenerator(
name=datasets.Split.TEST,
gen_kwargs={
"filepaths": file_path["test"]
}
)
datasets.SplitGenerator(name=datasets.Split.TRAIN, gen_kwargs={"filepaths": file_path["train"]}),
datasets.SplitGenerator(name=datasets.Split.TEST, gen_kwargs={"filepaths": file_path["test"]}),
]
def _generate_examples(self, filepaths: List[str]):
@@ -70,12 +59,12 @@ class HhRlhfEn(datasets.GeneratorBasedBuilder):
rejected = data["rejected"]
assist_idx = rejected.rfind("\n\nAssistant: ")
r_reject = rejected[assist_idx+13:].strip()
r_reject = rejected[assist_idx + 13 :].strip()
assist_idx = chosen.rfind("\n\nAssistant: ")
r_accept = chosen[assist_idx+13:].strip()
r_accept = chosen[assist_idx + 13 :].strip()
human_idx = chosen.rfind("\n\nHuman: ")
query = chosen[human_idx+9:assist_idx].strip()
query = chosen[human_idx + 9 : assist_idx].strip()
prompt = chosen[:human_idx]
history = []
@@ -83,16 +72,12 @@ class HhRlhfEn(datasets.GeneratorBasedBuilder):
assist_idx = prompt.rfind("\n\nAssistant: ")
human_idx = prompt.rfind("\n\nHuman: ")
if human_idx != -1:
old_query = prompt[human_idx+9:assist_idx].strip()
old_resp = prompt[assist_idx+13:].strip()
old_query = prompt[human_idx + 9 : assist_idx].strip()
old_resp = prompt[assist_idx + 13 :].strip()
history.insert(0, (old_query, old_resp))
else:
break
prompt = prompt[:human_idx]
yield key, {
"instruction": query,
"output": [r_accept, r_reject],
"history": history
}
yield key, {"instruction": query, "output": [r_accept, r_reject], "history": history}
key += 1