Spaces:
Build error
Build error
File size: 4,267 Bytes
cd32184 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 |
# Copyright 2024 the LlamaFactory team.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from typing import TYPE_CHECKING, Any, Dict, List, Optional, Sequence, Tuple
from ...extras.logging import get_logger
from ..data_utils import Role
from .processor_utils import get_paligemma_token_type_ids, get_pixel_values, infer_seqlen
if TYPE_CHECKING:
from transformers import PreTrainedTokenizer, ProcessorMixin
from ...hparams import DataArguments
from ..template import Template
logger = get_logger(__name__)
def _encode_unsupervised_example(
prompt: Sequence[Dict[str, str]],
response: Sequence[Dict[str, str]],
system: Optional[str],
tools: Optional[str],
template: "Template",
tokenizer: "PreTrainedTokenizer",
processor: Optional["ProcessorMixin"],
data_args: "DataArguments",
) -> Tuple[List[int], List[int]]:
if processor is not None and not hasattr(processor, "image_seq_length"): # llava-like models
prompt[0]["content"] = template.image_token + prompt[0]["content"]
if len(response) == 1:
messages = prompt + response
else:
messages = prompt + [{"role": Role.ASSISTANT.value, "content": ""}]
input_ids, labels = template.encode_oneturn(tokenizer, messages, system, tools)
if template.efficient_eos:
labels += [tokenizer.eos_token_id]
if processor is not None and hasattr(processor, "image_seq_length"): # paligemma models
image_token_id = tokenizer.convert_tokens_to_ids(template.image_token)
input_ids = [image_token_id] * getattr(processor, "image_seq_length") + input_ids
source_len, target_len = infer_seqlen(len(input_ids), len(labels), data_args.cutoff_len)
input_ids = input_ids[:source_len]
labels = labels[:target_len]
return input_ids, labels
def preprocess_unsupervised_dataset(
examples: Dict[str, List[Any]],
template: "Template",
tokenizer: "PreTrainedTokenizer",
processor: Optional["ProcessorMixin"],
data_args: "DataArguments",
) -> Dict[str, List[List[int]]]:
# build inputs with format `<bos> X` and labels with format `Y <eos>`
model_inputs = {"input_ids": [], "attention_mask": [], "labels": []}
if processor is not None:
model_inputs["pixel_values"] = []
if hasattr(processor, "image_seq_length"): # paligemma models
model_inputs["token_type_ids"] = []
for i in range(len(examples["prompt"])):
if len(examples["prompt"][i]) % 2 != 1:
logger.warning("Dropped invalid example: {}".format(examples["prompt"][i] + examples["response"][i]))
continue
input_ids, labels = _encode_unsupervised_example(
prompt=examples["prompt"][i],
response=examples["response"][i],
system=examples["system"][i],
tools=examples["tools"][i],
template=template,
tokenizer=tokenizer,
processor=processor,
data_args=data_args,
)
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:
model_inputs["pixel_values"].append(get_pixel_values(examples["images"][i], processor))
if hasattr(processor, "image_seq_length"): # paligemma models
model_inputs["token_type_ids"].append(get_paligemma_token_type_ids(len(input_ids), processor))
return model_inputs
def print_unsupervised_dataset_example(example: Dict[str, List[int]], tokenizer: "PreTrainedTokenizer") -> None:
print("input_ids:\n{}".format(example["input_ids"]))
print("inputs:\n{}".format(tokenizer.decode(example["input_ids"], skip_special_tokens=False)))
|