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

modify code structure

Browse Source 
Former-commit-id: 6369f9b1751e6f9bb709ba76a85f69cbe0823e5d
This commit is contained in:
hiyouga
2023-08-02 23:17:36 +08:00
parent 8bd1da7144
commit 28a51b622b
25 changed files with 188 additions and 145 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
src/llmtuner/tuner/ppo/workflow.py
View File

@@ -10,7 +10,6 @@ from transformers import DataCollatorForSeq2Seq
from transformers.optimization import get_scheduler
from llmtuner.dsets import get_dataset, preprocess_dataset
from llmtuner.extras.callbacks import LogCallback
from llmtuner.extras.ploting import plot_loss
from llmtuner.tuner.core import load_model_and_tokenizer
from llmtuner.tuner.ppo.trainer import PPOPeftTrainer
@@ -25,7 +24,7 @@ def run_ppo(
data_args: "DataArguments",
training_args: "Seq2SeqTrainingArguments",
finetuning_args: "FinetuningArguments",
callbacks: Optional[List["TrainerCallback"]] = [LogCallback()]
callbacks: Optional[List["TrainerCallback"]] = None
):
dataset = get_dataset(model_args, data_args)
model, tokenizer = load_model_and_tokenizer(model_args, finetuning_args, training_args.do_train, stage="ppo")