423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-16 20:00:36 +08:00
Code Issues Packages Projects Releases Wiki Activity

support mllm hf inference

Browse Source
This commit is contained in:
hiyouga
2024-04-26 05:34:58 +08:00
parent c20f750d11
commit e057c8de48
27 changed files with 130 additions and 51 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -27,8 +27,9 @@ def run_ppo(
generating_args: "GeneratingArguments",
callbacks: Optional[List["TrainerCallback"]] = None,
):
tokenizer = load_tokenizer(model_args)
dataset = get_dataset(tokenizer, model_args, data_args, training_args, stage="ppo")
tokenizer_module = load_tokenizer(model_args)
tokenizer = tokenizer_module["tokenizer"]
dataset = 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