mirror of
https://github.com/hiyouga/LLaMA-Factory.git
synced 2025-10-15 08:08:09 +08:00
62 lines
2.5 KiB
Python
62 lines
2.5 KiB
Python
from typing import TYPE_CHECKING, Any, Dict, List, Optional
|
|
|
|
from llmtuner.extras.callbacks import LogCallback
|
|
from llmtuner.extras.logging import get_logger
|
|
from llmtuner.model import get_train_args, get_infer_args, load_model_and_tokenizer
|
|
from llmtuner.train.pt import run_pt
|
|
from llmtuner.train.sft import run_sft
|
|
from llmtuner.train.rm import run_rm
|
|
from llmtuner.train.ppo import run_ppo
|
|
from llmtuner.train.dpo import run_dpo
|
|
|
|
if TYPE_CHECKING:
|
|
from transformers import TrainerCallback
|
|
|
|
|
|
logger = get_logger(__name__)
|
|
|
|
|
|
def run_exp(args: Optional[Dict[str, Any]] = None, callbacks: Optional[List["TrainerCallback"]] = None):
|
|
model_args, data_args, training_args, finetuning_args, generating_args = get_train_args(args)
|
|
callbacks = [LogCallback()] if callbacks is None else callbacks
|
|
|
|
if finetuning_args.stage == "pt":
|
|
run_pt(model_args, data_args, training_args, finetuning_args, callbacks)
|
|
elif finetuning_args.stage == "sft":
|
|
run_sft(model_args, data_args, training_args, finetuning_args, generating_args, callbacks)
|
|
elif finetuning_args.stage == "rm":
|
|
run_rm(model_args, data_args, training_args, finetuning_args, callbacks)
|
|
elif finetuning_args.stage == "ppo":
|
|
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)
|
|
else:
|
|
raise ValueError("Unknown task.")
|
|
|
|
|
|
def export_model(args: Optional[Dict[str, Any]] = None):
|
|
model_args, _, finetuning_args, _ = get_infer_args(args)
|
|
|
|
if model_args.adapter_name_or_path is not None and model_args.export_quantization_bit is not None:
|
|
raise ValueError("Please merge adapters before quantizing the model.")
|
|
|
|
model, tokenizer = load_model_and_tokenizer(model_args, finetuning_args)
|
|
|
|
if getattr(model, "quantization_method", None) and model_args.adapter_name_or_path is not None:
|
|
logger.warning("Cannot merge adapters to a quantized model.")
|
|
|
|
model.config.use_cache = True
|
|
model = model.to("cpu")
|
|
model.save_pretrained(model_args.export_dir, max_shard_size="{}GB".format(model_args.export_size))
|
|
|
|
try:
|
|
tokenizer.padding_side = "left" # restore padding side
|
|
tokenizer.init_kwargs["padding_side"] = "left"
|
|
tokenizer.save_pretrained(model_args.export_dir)
|
|
except:
|
|
logger.warning("Cannot save tokenizer, please copy the files manually.")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
run_exp()
|