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

4
src/llamafactory/train/ppo/workflow.py
View File

@@ -41,11 +41,11 @@ def run_ppo(
):
tokenizer_module = load_tokenizer(model_args)
tokenizer = tokenizer_module["tokenizer"]
dataset_module = get_dataset(model_args, data_args, training_args, stage="ppo", **tokenizer_module)
dataset_module, template = get_dataset(model_args, data_args, training_args, stage="ppo", **tokenizer_module)
model = load_model(tokenizer, model_args, finetuning_args, training_args.do_train, add_valuehead=True)
tokenizer.padding_side = "left" # use left-padding in generation while using right-padding in training
data_collator = MultiModalDataCollatorForSeq2Seq(tokenizer=tokenizer)
data_collator = MultiModalDataCollatorForSeq2Seq(template=template, **tokenizer_module)
# Create reference model and reward model
ref_model = create_ref_model(model_args, finetuning_args, add_valuehead=True)