423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-28 01:30:36 +08:00
Code Issues Packages Projects Releases Wiki Activity

refactor export, fix #1190

Browse Source 
Former-commit-id: 30e60e37023a7c4a2db033ffec0542efa3d5cdfb
This commit is contained in:
hiyouga
2023-10-15 16:01:48 +08:00
parent 68330eab2a
commit c2e84d4558
9 changed files with 52 additions and 49 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
src/llmtuner/tuner/tune.py
View File

@@ -2,7 +2,7 @@ from typing import TYPE_CHECKING, Any, Dict, List, Optional
from llmtuner.extras.callbacks import LogCallback
from llmtuner.extras.logging import get_logger
from llmtuner.tuner.core import get_train_args, load_model_and_tokenizer
from llmtuner.tuner.core import get_train_args, get_infer_args, load_model_and_tokenizer
from llmtuner.tuner.pt import run_pt
from llmtuner.tuner.sft import run_sft
from llmtuner.tuner.rm import run_rm
@@ -17,31 +17,32 @@ 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, general_args = get_train_args(args)
model_args, data_args, training_args, finetuning_args, generating_args = get_train_args(args)
callbacks = [LogCallback()] if callbacks is None else callbacks
if general_args.stage == "pt":
if finetuning_args.stage == "pt":
run_pt(model_args, data_args, training_args, finetuning_args, callbacks)
elif general_args.stage == "sft":
elif finetuning_args.stage == "sft":
run_sft(model_args, data_args, training_args, finetuning_args, generating_args, callbacks)
elif general_args.stage == "rm":
elif finetuning_args.stage == "rm":
run_rm(model_args, data_args, training_args, finetuning_args, callbacks)
elif general_args.stage == "ppo":
elif finetuning_args.stage == "ppo":
run_ppo(model_args, data_args, training_args, finetuning_args, generating_args, callbacks)
elif general_args.stage == "dpo":
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, max_shard_size: Optional[str] = "10GB"):
model_args, _, training_args, finetuning_args, _, _ = get_train_args(args)
model_args, _, finetuning_args, _ = get_infer_args(args)
model, tokenizer = load_model_and_tokenizer(model_args, finetuning_args)
model.config.use_cache = True
tokenizer.padding_side = "left" # restore padding side
tokenizer.init_kwargs["padding_side"] = "left"
model.save_pretrained(training_args.output_dir, max_shard_size=max_shard_size)
model.save_pretrained(model_args.export_dir, max_shard_size=max_shard_size)
try:
tokenizer.save_pretrained(training_args.output_dir)
tokenizer.save_pretrained(model_args.export_dir)
except:
logger.warning("Cannot save tokenizer, please copy the files manually.")