tiny fix

Former-commit-id: 830511a6d0216da99520aee8b3a753d347a71fa9

src/llamafactory/data/processors/feedback.py

@@ -84,7 +84,7 @@ def preprocess_feedback_dataset(
     tokenizer: "PreTrainedTokenizer",
     processor: Optional["ProcessorMixin"],
     data_args: "DataArguments",
-) -> Dict[str, List[List[int]]]:
+) -> Dict[str, List[Any]]:
     # create unrelated input-output pairs for estimating the KL term by flipping the matched pairs
     kl_response = examples["response"][::-1]
     model_inputs = defaultdict(list)

src/llamafactory/data/processors/pairwise.py

@@ -70,7 +70,7 @@ def preprocess_pairwise_dataset(
     tokenizer: "PreTrainedTokenizer",
     processor: Optional["ProcessorMixin"],
     data_args: "DataArguments",
-) -> Dict[str, List[List[int]]]:
+) -> Dict[str, List[Any]]:
     # build input pairs with format `<bos> X`, `Y1 <eos>` and `Y2 <eos>`
     model_inputs = defaultdict(list)
     for i in range(len(examples["prompt"])):

src/llamafactory/data/processors/pretrain.py

@@ -27,7 +27,7 @@ if TYPE_CHECKING:
 
 def preprocess_pretrain_dataset(
     examples: Dict[str, List[Any]], tokenizer: "PreTrainedTokenizer", data_args: "DataArguments"
-) -> Dict[str, List[List[int]]]:
+) -> Dict[str, List[Any]]:
     # build grouped texts with format `X1 X2 X3 ...` if packing is enabled
     eos_token = "<|end_of_text|>" if data_args.template == "llama3" else tokenizer.eos_token
     text_examples = [messages[0]["content"] + eos_token for messages in examples["prompt"]]

src/llamafactory/data/processors/unsupervised.py

@@ -62,7 +62,7 @@ def preprocess_unsupervised_dataset(
     tokenizer: "PreTrainedTokenizer",
     processor: Optional["ProcessorMixin"],
     data_args: "DataArguments",
-) -> Dict[str, List[List[int]]]:
+) -> Dict[str, List[Any]]:
     # build inputs with format `<bos> X` and labels with format `Y <eos>`
     model_inputs = defaultdict(list)
     for i in range(len(examples["prompt"])):