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

lazy image load

Browse Source 
Former-commit-id: cdd733b575411e003bc5ffd6560dd8eff8aa09cf
This commit is contained in:
hiyouga
2024-09-04 02:27:08 +08:00
parent fed7ae5661
commit 7056087e92
19 changed files with 353 additions and 366 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
src/llamafactory/train/rm/workflow.py
View File

@@ -41,12 +41,12 @@ def run_rm(
):
tokenizer_module = load_tokenizer(model_args)
tokenizer = tokenizer_module["tokenizer"]
dataset_module = get_dataset(model_args, data_args, training_args, stage="rm", **tokenizer_module)
dataset_module, template = get_dataset(model_args, data_args, training_args, stage="rm", **tokenizer_module)
model = load_model(tokenizer, model_args, finetuning_args, training_args.do_train, add_valuehead=True)
data_collator = PairwiseDataCollatorWithPadding(tokenizer, pad_to_multiple_of=8)
data_collator = PairwiseDataCollatorWithPadding(template=template, pad_to_multiple_of=8, **tokenizer_module)
# Update arguments
training_args.remove_unused_columns = False # important for pairwise dataset
training_args.remove_unused_columns = False # important for multimodal and pairwise dataset
# Initialize our Trainer
trainer = PairwiseTrainer(