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

fix #2649

Browse Source 
Former-commit-id: 1c850de660c671d92f0bc63f230d338b60b7c0bd
This commit is contained in:
hiyouga
2024-03-01 13:02:41 +08:00
parent 5306a71b42
commit 59a9a5994e
9 changed files with 99 additions and 87 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
src/llmtuner/train/pt/workflow.py
View File

@@ -7,7 +7,7 @@ from transformers import DataCollatorForLanguageModeling, Trainer
from ...data import get_dataset, split_dataset
from ...extras.ploting import plot_loss
from ...model import load_model_and_tokenizer
from ...model import load_model, load_tokenizer
from ...train.utils import create_modelcard_and_push
@@ -24,8 +24,9 @@ def run_pt(
finetuning_args: "FinetuningArguments",
callbacks: Optional[List["TrainerCallback"]] = None,
):
model, tokenizer = load_model_and_tokenizer(model_args, finetuning_args, training_args.do_train)
tokenizer = load_tokenizer(model_args)
dataset = get_dataset(tokenizer, model_args, data_args, training_args, stage="pt")
model = load_model(tokenizer, model_args, finetuning_args, training_args.do_train)
data_collator = DataCollatorForLanguageModeling(tokenizer=tokenizer, mlm=False)
# Initialize our Trainer