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

Merge branch 'hiyouga:main' into pixtral-patch

Browse Source 
Former-commit-id: 28696e2f945a9f55e4ca9e9dc5ebd8af9df45d8b
This commit is contained in:
Kingsley
2024-10-13 17:42:02 +08:00
committed by GitHub
parent be519c84d9 74dd25224a
commit 313a5e1494
16 changed files with 137 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
src/llamafactory/data/loader.py
View File

@@ -53,7 +53,7 @@ def _load_single_dataset(
"""
logger.info("Loading dataset {}...".format(dataset_attr))
data_path, data_name, data_dir, data_files = None, None, None, None
if dataset_attr.load_from in ["hf_hub", "ms_hub"]:
if dataset_attr.load_from in ["hf_hub", "ms_hub", "om_hub"]:
data_path = dataset_attr.dataset_name
data_name = dataset_attr.subset
data_dir = dataset_attr.folder
@@ -102,6 +102,23 @@ def _load_single_dataset(
)
if isinstance(dataset, MsDataset):
dataset = dataset.to_hf_dataset()
elif dataset_attr.load_from == "om_hub":
require_version("openmind>=0.8.0", "To fix: pip install openmind>=0.8.0")
from openmind import OmDataset
from openmind.utils.hub import OM_DATASETS_CACHE
cache_dir = model_args.cache_dir or OM_DATASETS_CACHE
dataset = OmDataset.load_dataset(
path=data_path,
name=data_name,
data_dir=data_dir,
data_files=data_files,
split=dataset_attr.split,
cache_dir=cache_dir,
token=model_args.om_hub_token,
streaming=(data_args.streaming and (dataset_attr.load_from != "file")),
)
else:
dataset = load_dataset(
path=data_path,

18
src/llamafactory/data/parser.py
View File

@@ -20,7 +20,7 @@ from typing import Any, Dict, List, Literal, Optional, Sequence
from transformers.utils import cached_file
from ..extras.constants import DATA_CONFIG
from ..extras.misc import use_modelscope
from ..extras.misc import use_modelscope, use_openmind
@dataclass
@@ -30,7 +30,7 @@ class DatasetAttr:
"""
# basic configs
load_from: Literal["hf_hub", "ms_hub", "script", "file"]
load_from: Literal["hf_hub", "ms_hub", "om_hub", "script", "file"]
dataset_name: str
formatting: Literal["alpaca", "sharegpt"] = "alpaca"
ranking: bool = False
@@ -98,7 +98,12 @@ def get_dataset_list(dataset_names: Optional[Sequence[str]], dataset_dir: str) -
dataset_list: List["DatasetAttr"] = []
for name in dataset_names:
if dataset_info is None: # dataset_dir is ONLINE
load_from = "ms_hub" if use_modelscope() else "hf_hub"
if use_modelscope():
load_from = "ms_hub"
elif use_openmind():
load_from = "om_hub"
else:
load_from = "hf_hub"
dataset_attr = DatasetAttr(load_from, dataset_name=name)
dataset_list.append(dataset_attr)
continue
@@ -108,10 +113,13 @@ def get_dataset_list(dataset_names: Optional[Sequence[str]], dataset_dir: str) -
has_hf_url = "hf_hub_url" in dataset_info[name]
has_ms_url = "ms_hub_url" in dataset_info[name]
has_om_url = "om_hub_url" in dataset_info[name]
if has_hf_url or has_ms_url:
if (use_modelscope() and has_ms_url) or (not has_hf_url):
if has_hf_url or has_ms_url or has_om_url:
if has_ms_url and (use_modelscope() or not has_hf_url):
dataset_attr = DatasetAttr("ms_hub", dataset_name=dataset_info[name]["ms_hub_url"])
elif has_om_url and (use_openmind() or not has_hf_url):
dataset_attr = DatasetAttr("om_hub", dataset_name=dataset_info[name]["om_hub_url"])
else:
dataset_attr = DatasetAttr("hf_hub", dataset_name=dataset_info[name]["hf_hub_url"])
elif "script_url" in dataset_info[name]: