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

merge some func

Browse Source 
Former-commit-id: 3085107c44715e4b2ca96d73b20d90c172b95219
This commit is contained in:
BUAADreamer
2024-04-25 22:35:17 +08:00
parent 514ffafc12
commit 759bee48d2
3 changed files with 10 additions and 205 deletions
Download Patch File Download Diff File Expand all files Collapse all files

65
src/llmtuner/data/preprocess.py
View File

@@ -50,6 +50,7 @@ def preprocess_supervised_dataset(
tokenizer: "PreTrainedTokenizer",
template: "Template",
data_args: "DataArguments",
processor: "AutoProcessor" = None,
) -> Dict[str, List[List[int]]]:
# build inputs with format `<bos> X Y <eos>` and labels with format `<ignore> ... <ignore> Y <eos>`
# for multiturn examples, we only mask the prompt part in each prompt-response pair.
@@ -88,7 +89,9 @@ def preprocess_supervised_dataset(
model_inputs["input_ids"].append(input_ids)
model_inputs["attention_mask"].append([1] * len(input_ids))
model_inputs["labels"].append(labels)
if processor is not None and "images" in examples:
pixel_values = processor.image_processor(examples["images"][0], return_tensors="pt")["pixel_values"][0]
model_inputs["pixel_values"].append(pixel_values)
return model_inputs
@@ -138,55 +141,6 @@ def preprocess_packed_supervised_dataset(
return model_inputs
def preprocess_multimodal_supervised_dataset(
examples: Dict[str, List[Any]],
processor: "AutoProcessor",
template: "Template",
data_args: "DataArguments",
) -> Dict[str, List[List[int]]]:
# build inputs with format `<bos> X Y <eos>` and labels with format `<ignore> ... <ignore> Y <eos>`
# for multiturn examples, we only mask the prompt part in each prompt-response pair.
tokenizer = processor.tokenizer
model_inputs = {"input_ids": [], "attention_mask": [], "labels": [], "pixel_values": []}
for i in range(len(examples["prompt"])):
if len(examples["prompt"][i]) % 2 != 1 or len(examples["response"][i]) != 1:
continue
messages = examples["prompt"][i] + examples["response"][i]
input_ids, labels = [], []
for turn_idx, (source_ids, target_ids) in enumerate(
template.encode_multiturn(
tokenizer,
messages,
examples["system"][i],
examples["tools"][i],
data_args.cutoff_len,
data_args.reserved_label_len,
)
):
if data_args.train_on_prompt:
source_mask = source_ids
elif turn_idx != 0 and template.efficient_eos:
source_mask = [tokenizer.eos_token_id] + [IGNORE_INDEX] * (len(source_ids) - 1)
else:
source_mask = [IGNORE_INDEX] * len(source_ids)
input_ids += source_ids + target_ids
labels += source_mask + target_ids
if template.efficient_eos:
input_ids += [tokenizer.eos_token_id]
labels += [tokenizer.eos_token_id]
model_inputs["input_ids"].append(input_ids)
model_inputs["attention_mask"].append([1] * len(input_ids))
model_inputs["labels"].append(labels)
pixel_values = processor.image_processor(examples["images"][0], return_tensors="pt")["pixel_values"][0]
model_inputs["pixel_values"].append(pixel_values)
return model_inputs
def preprocess_unsupervised_dataset(
examples: Dict[str, List[Any]],
tokenizer: "PreTrainedTokenizer",
@@ -307,15 +261,14 @@ def get_preprocess_and_print_func(
preprocess_func = partial(
preprocess_packed_supervised_dataset, tokenizer=tokenizer, template=template, data_args=data_args
)
elif processor is not None:
preprocess_func = partial(
preprocess_multimodal_supervised_dataset, processor=processor, template=template, data_args=data_args
)
else:
preprocess_func = partial(
preprocess_supervised_dataset, tokenizer=tokenizer, template=template, data_args=data_args
preprocess_supervised_dataset,
tokenizer=tokenizer,
template=template,
data_args=data_args,
processor=processor,
)
print_function = partial(print_supervised_dataset_example, tokenizer=tokenizer)
elif stage == "rm":
preprocess_func = partial(