423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-16 20:00:36 +08:00
Code Issues Packages Projects Releases Wiki Activity

improve KTO impl., replace datasets

Browse Source
This commit is contained in:
hiyouga
2024-05-18 03:44:56 +08:00
parent 33a354548e
commit c450ee87a3
65 changed files with 46415 additions and 2035053 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
src/llamafactory/train/tuner.py
View File

@@ -9,12 +9,13 @@ from ..extras.logging import get_logger
from ..hparams import get_infer_args, get_train_args
from ..model import load_model, load_tokenizer
from .dpo import run_dpo
from .kto import run_kto
from .orpo import run_orpo
from .ppo import run_ppo
from .pt import run_pt
from .rm import run_rm
from .sft import run_sft
from .kto import run_kto
if TYPE_CHECKING:
from transformers import TrainerCallback
@@ -37,10 +38,10 @@ def run_exp(args: Optional[Dict[str, Any]] = None, callbacks: List["TrainerCallb
run_ppo(model_args, data_args, training_args, finetuning_args, generating_args, callbacks)
elif finetuning_args.stage == "dpo":
run_dpo(model_args, data_args, training_args, finetuning_args, callbacks)
elif finetuning_args.stage == "orpo":
run_orpo(model_args, data_args, training_args, finetuning_args, callbacks)
elif finetuning_args.stage == "kto":
run_kto(model_args, data_args, training_args, finetuning_args, callbacks)
elif finetuning_args.stage == "orpo":
run_orpo(model_args, data_args, training_args, finetuning_args, callbacks)
else:
raise ValueError("Unknown task.")