跳转至

DNABERT

DNABERT

Pre-trained model on human genome using a masked language modeling (MLM) objective with k-mer tokenization.

Disclaimer

This is an UNOFFICIAL implementation of the DNABERT: pre-trained Bidirectional Encoder Representations from Transformers model for DNA-language in genome by Yanrong Ji, Zhihan Zhou, et al.

The OFFICIAL repository of DNABERT is at jerryji1993/DNABERT.

Tip

The MultiMolecule team has confirmed that the provided model and checkpoints are producing the same intermediate representations as the original implementation.

The team releasing DNABERT did not write this model card for this model so this model card has been written by the MultiMolecule team.

Model Details

DNABERT is a bert-style model pre-trained on the human genome with k-mer tokenization in a self-supervised fashion. This means that the model was trained on the raw nucleotides of DNA sequences only, with an automatic process to generate inputs and labels from those texts. Please refer to the Training Details section for more information on the training process.

Variants

Model Specification

Variants Num Layers Hidden Size Num Heads Intermediate Size Num Parameters (M) FLOPs (G) MACs (G) Max Num Tokens
dnabert-6mer 12 768 12 3072 89.19 96.86 48.43 512
dnabert-5mer 86.83
dnabert-4mer 86.24
dnabert-3mer 86.10

Usage

The model file depends on the multimolecule library. You can install it using pip:

Bash
1
pip install multimolecule

Direct Use

Masked Language Modeling

Warning

Default transformers pipeline does not support K-mer tokenization.

You can use this model directly with a pipeline for masked language modeling:

Python
1
2
3
4
5
import multimolecule  # you must import multimolecule to register models
from transformers import pipeline

predictor = pipeline("fill-mask", model="multimolecule/dnabert")
output = predictor("ATCG<mask>TGCA")

Downstream Use

Extract Features

Here is how to use this model to get the features of a given sequence in PyTorch:

Python
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
from multimolecule import DnaBertModel
from transformers import AutoTokenizer


tokenizer = AutoTokenizer.from_pretrained("multimolecule/dnabert")
model = DnaBertModel.from_pretrained("multimolecule/dnabert")

text = "ATCGATCGATCGATCG"
input = tokenizer(text, return_tensors="pt")

output = model(**input)

Sequence Classification / Regression

Note

This model is not fine-tuned for any specific task. You will need to fine-tune the model on a downstream task to use it for sequence classification or regression.

Here is how to use this model as backbone to fine-tune for a sequence-level task in PyTorch:

Python
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
import torch
from multimolecule import DnaBertForSequencePrediction
from transformers import AutoTokenizer


tokenizer = AutoTokenizer.from_pretrained("multimolecule/dnabert")
model = DnaBertForSequencePrediction.from_pretrained("multimolecule/dnabert")

text = "ATCGATCGATCGATCG"
input = tokenizer(text, return_tensors="pt")
label = torch.tensor([1])

output = model(**input, labels=label)

Token Classification / Regression

Note

This model is not fine-tuned for any specific task. You will need to fine-tune the model on a downstream task to use it for token classification or regression.

Here is how to use this model as backbone to fine-tune for a nucleotide-level task in PyTorch:

Python
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
import torch
from multimolecule import DnaBertForTokenPrediction
from transformers import AutoTokenizer


tokenizer = AutoTokenizer.from_pretrained("multimolecule/dnabert")
model = DnaBertForTokenPrediction.from_pretrained("multimolecule/dnabert")

text = "ATCGATCGATCGATCG"
input = tokenizer(text, return_tensors="pt")
label = torch.randint(2, (len(text), ))

output = model(**input, labels=label)

Contact Classification / Regression

Note

This model is not fine-tuned for any specific task. You will need to fine-tune the model on a downstream task to use it for contact classification or regression.

Here is how to use this model as backbone to fine-tune for a contact-level task in PyTorch:

Python
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
import torch
from multimolecule import DnaBertForContactPrediction
from transformers import AutoTokenizer


tokenizer = AutoTokenizer.from_pretrained("multimolecule/dnabert")
model = DnaBertForContactPrediction.from_pretrained("multimolecule/dnabert")

text = "ATCGATCGATCGATCG"
input = tokenizer(text, return_tensors="pt")
label = torch.randint(2, (len(text), len(text)))

output = model(**input, labels=label)

Training Details

DNABERT used Masked Language Modeling (MLM) as the pre-training objective: taking a sequence, the model randomly masks 15% of the tokens in the input then runs the entire masked sentence through the model and has to predict the masked tokens. This is comparable to the Cloze task in language modeling.

Training Data

The DNABERT model was pre-trained on the human genome. The training data consists of DNA sequences from the human reference genome (GRCh38.p13), with all sequences containing only the four canonical nucleotides (A, T, C, G).

Training Procedure

Preprocessing

DNABERT used masked language modeling (MLM) as the pre-training objective. The masking procedure is similar to the one used in BERT:

  • Mask rate: 15%, increased to 20% for the last 20,000 steps
  • Replacement: <mask> for 80% of masked tokens
  • Replacement: random token for 10% of masked tokens
  • Replacement: unchanged token for 10% of masked tokens

Since DNABERT used k-mer tokenizer, it masks the entire k-mer instead of individual nucleotides to avoid information leakage.

For example, if the k-mer is 3, the sequence "TAGCGTAT" will be tokenized as ["TAG", "AGC", "GCG", "CGT", "GTA", "TAT"]. If the nucleotide "C" is masked, the adjacent tokens will also be masked, resulting ["TAG", "<mask>", "<mask>", "<mask>", "GTA", "TAT"].

Pre-training

The model was trained on 8 NVIDIA RTX 2080Ti GPUs.

  • Batch size: 2,000
  • Steps: 120,000
  • Learning rate: 4e-4
  • Learning rate scheduler: Linear
  • Learning rate warm-up: 10,000 steps

Citation

BibTeX
 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
@ARTICLE{Ji2021-cj,
  title     = "{DNABERT}: pre-trained Bidirectional Encoder Representations
               from Transformers model for {DNA-language} in genome",
  author    = "Ji, Yanrong and Zhou, Zhihan and Liu, Han and Davuluri, Ramana V",
  abstract  = "MOTIVATION: Deciphering the language of non-coding DNA is one of
               the fundamental problems in genome research. Gene regulatory
               code is highly complex due to the existence of polysemy and
               distant semantic relationship, which previous informatics
               methods often fail to capture especially in data-scarce
               scenarios. RESULTS: To address this challenge, we developed a
               novel pre-trained bidirectional encoder representation, named
               DNABERT, to capture global and transferrable understanding of
               genomic DNA sequences based on up and downstream nucleotide
               contexts. We compared DNABERT to the most widely used programs
               for genome-wide regulatory elements prediction and demonstrate
               its ease of use, accuracy and efficiency. We show that the
               single pre-trained transformers model can simultaneously achieve
               state-of-the-art performance on prediction of promoters, splice
               sites and transcription factor binding sites, after easy
               fine-tuning using small task-specific labeled data. Further,
               DNABERT enables direct visualization of nucleotide-level
               importance and semantic relationship within input sequences for
               better interpretability and accurate identification of conserved
               sequence motifs and functional genetic variant candidates.
               Finally, we demonstrate that pre-trained DNABERT with human
               genome can even be readily applied to other organisms with
               exceptional performance. We anticipate that the pre-trained
               DNABERT model can be fined tuned to many other sequence analyses
               tasks. AVAILABILITY AND IMPLEMENTATION: The source code,
               pretrained and finetuned model for DNABERT are available at
               GitHub (https://github.com/jerryji1993/DNABERT). SUPPLEMENTARY
               INFORMATION: Supplementary data are available at Bioinformatics
               online.",
  journal   = "Bioinformatics",
  publisher = "Oxford University Press (OUP)",
  volume    =  37,
  number    =  15,
  pages     = "2112--2120",
  month     =  aug,
  year      =  2021,
  copyright = "https://academic.oup.com/journals/pages/open\_access/funder\_policies/chorus/standard\_publication\_model",
  language  = "en"
}

Note

The artifacts distributed in this repository are part of the MultiMolecule project. If you use MultiMolecule in your research, you must cite the MultiMolecule project as follows:

BibTeX
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
@software{chen_2024_12638419,
  author    = {Chen, Zhiyuan and Zhu, Sophia Y.},
  title     = {MultiMolecule},
  doi       = {10.5281/zenodo.12638419},
  publisher = {Zenodo},
  url       = {https://doi.org/10.5281/zenodo.12638419},
  year      = 2024,
  month     = may,
  day       = 4
}

Contact

Please use GitHub issues of MultiMolecule for any questions or comments on the model card.

Please contact the authors of the DNABERT paper for questions or comments on the paper/model.

License

This model implementation is licensed under the GNU Affero General Public License.

For additional terms and clarifications, please refer to our License FAQ.

Text Only
1
SPDX-License-Identifier: AGPL-3.0-or-later

multimolecule.models.dnabert

DnaTokenizer

Bases: Tokenizer

Tokenizer for DNA sequences.

Parameters:

Name Type Description Default

alphabet

Alphabet | str | List[str] | None

alphabet to use for tokenization.

  • If is None, the standard RNA alphabet will be used.
  • If is a string, it should correspond to the name of a predefined alphabet. The options include
    • standard
    • iupac
    • streamline
    • nucleobase
  • If is an alphabet or a list of characters, that specific alphabet will be used.
 None

nmers

int

Size of kmer to tokenize.

 1

codon

bool

Whether to tokenize into codons.

 False

replace_U_with_T

bool

Whether to replace U with T.

 True

do_upper_case

bool

Whether to convert input to uppercase.

 True

Examples:

Python Console Session
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
>>> from multimolecule import DnaTokenizer
>>> tokenizer = DnaTokenizer()
>>> tokenizer('<pad><cls><eos><unk><mask><null>ACGTNRYSWKMBDHVX|.*-?')["input_ids"]
[1, 0, 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, 2]
>>> tokenizer('acgt')["input_ids"]
[1, 6, 7, 8, 9, 2]
>>> tokenizer('acgu')["input_ids"]
[1, 6, 7, 8, 9, 2]
>>> tokenizer = DnaTokenizer(replace_U_with_T=False)
>>> tokenizer('acgu')["input_ids"]
[1, 6, 7, 8, 3, 2]
>>> tokenizer = DnaTokenizer(nmers=3)
>>> tokenizer('tataaagta')["input_ids"]
[1, 84, 21, 81, 6, 8, 19, 71, 2]
>>> tokenizer = DnaTokenizer(codon=True)
>>> tokenizer('tataaagta')["input_ids"]
[1, 84, 6, 71, 2]
>>> tokenizer('tataaagtaa')["input_ids"]
Traceback (most recent call last):
ValueError: length of input sequence must be a multiple of 3 for codon tokenization, but got 10
Source code in multimolecule/tokenisers/dna/tokenization_dna.py
Python
 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
108
109
110
111
112
113
114
115
116
117
118
class DnaTokenizer(Tokenizer):
    """
    Tokenizer for DNA sequences.

    Args:
        alphabet: alphabet to use for tokenization.

            - If is `None`, the standard RNA alphabet will be used.
            - If is a `string`, it should correspond to the name of a predefined alphabet. The options include
                + `standard`
                + `iupac`
                + `streamline`
                + `nucleobase`
            - If is an alphabet or a list of characters, that specific alphabet will be used.
        nmers: Size of kmer to tokenize.
        codon: Whether to tokenize into codons.
        replace_U_with_T: Whether to replace U with T.
        do_upper_case: Whether to convert input to uppercase.

    Examples:
        >>> from multimolecule import DnaTokenizer
        >>> tokenizer = DnaTokenizer()
        >>> tokenizer('<pad><cls><eos><unk><mask><null>ACGTNRYSWKMBDHVX|.*-?')["input_ids"]
        [1, 0, 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, 2]
        >>> tokenizer('acgt')["input_ids"]
        [1, 6, 7, 8, 9, 2]
        >>> tokenizer('acgu')["input_ids"]
        [1, 6, 7, 8, 9, 2]
        >>> tokenizer = DnaTokenizer(replace_U_with_T=False)
        >>> tokenizer('acgu')["input_ids"]
        [1, 6, 7, 8, 3, 2]
        >>> tokenizer = DnaTokenizer(nmers=3)
        >>> tokenizer('tataaagta')["input_ids"]
        [1, 84, 21, 81, 6, 8, 19, 71, 2]
        >>> tokenizer = DnaTokenizer(codon=True)
        >>> tokenizer('tataaagta')["input_ids"]
        [1, 84, 6, 71, 2]
        >>> tokenizer('tataaagtaa')["input_ids"]
        Traceback (most recent call last):
        ValueError: length of input sequence must be a multiple of 3 for codon tokenization, but got 10
    """

    model_input_names = ["input_ids", "attention_mask"]

    def __init__(
        self,
        alphabet: Alphabet | str | List[str] | None = None,
        nmers: int = 1,
        codon: bool = False,
        replace_U_with_T: bool = True,
        do_upper_case: bool = True,
        additional_special_tokens: List | Tuple | None = None,
        **kwargs,
    ):
        if codon and (nmers > 1 and nmers != 3):
            raise ValueError("Codon and nmers cannot be used together.")
        if codon:
            nmers = 3  # set to 3 to get correct vocab
        if not isinstance(alphabet, Alphabet):
            alphabet = get_alphabet(alphabet, nmers=nmers)
        super().__init__(
            alphabet=alphabet,
            nmers=nmers,
            codon=codon,
            replace_U_with_T=replace_U_with_T,
            do_upper_case=do_upper_case,
            additional_special_tokens=additional_special_tokens,
            **kwargs,
        )
        self.replace_U_with_T = replace_U_with_T
        self.nmers = nmers
        self.codon = codon

    def _tokenize(self, text: str, **kwargs):
        if self.do_upper_case:
            text = text.upper()
        if self.replace_U_with_T:
            text = text.replace("U", "T")
        if self.codon:
            if len(text) % 3 != 0:
                raise ValueError(
                    f"length of input sequence must be a multiple of 3 for codon tokenization, but got {len(text)}"
                )
            return [text[i : i + 3] for i in range(0, len(text), 3)]
        if self.nmers > 1:
            return [text[i : i + self.nmers] for i in range(len(text) - self.nmers + 1)]  # noqa: E203
        return list(text)

DnaBertConfig

Bases: PreTrainedConfig

This is the configuration class to store the configuration of a DnaBertModel. It is used to instantiate a DnaBert model according to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will yield a similar configuration to that of the DNABERT zhihan1996/DNA_bert_6 architecture.

Configuration objects inherit from PreTrainedConfig and can be used to control the model outputs. Read the documentation from PreTrainedConfig for more information.

Parameters:

Name Type Description Default

vocab_size

int

Vocabulary size of the DnaBert model. Defines the number of different tokens that can be represented by the input_ids passed when calling [DnaBertModel].

 4102

hidden_size

int

Dimensionality of the encoder layers and the pooler layer.

 768

num_hidden_layers

int

Number of hidden layers in the Transformer encoder.

 12

num_attention_heads

int

Number of attention heads for each attention layer in the Transformer encoder.

 12

intermediate_size

int

Dimensionality of the “intermediate” (often named feed-forward) layer in the Transformer encoder.

 3072

hidden_act

str

The non-linear activation function (function or string) in the encoder and pooler. If string, "gelu", "relu", "silu" and "gelu_new" are supported.

 'gelu'

hidden_dropout

float

The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.

 0.1

attention_dropout

float

The dropout ratio for the attention probabilities.

 0.1

max_position_embeddings

int

The maximum sequence length that this model might ever be used with. Typically set this to something large just in case (e.g., 512 or 1024 or 2048).

 512

initializer_range

float

The standard deviation of the truncated_normal_initializer for initializing all weight matrices.

 0.02

layer_norm_eps

float

The epsilon used by the layer normalization layers.

 1e-12

position_embedding_type

str

Type of position embedding. Choose one of "absolute", "relative_key", "relative_key_query". For positional embeddings use "absolute". For more information on "relative_key", please refer to Self-Attention with Relative Position Representations (Shaw et al.). For more information on "relative_key_query", please refer to Method 4 in Improve Transformer Models with Better Relative Position Embeddings (Huang et al.).

 'absolute'

is_decoder

bool

Whether the model is used as a decoder or not. If False, the model is used as an encoder.

 False

use_cache

bool

Whether or not the model should return the last key/values attentions (not used by all models). Only relevant if config.is_decoder=True.

 True

head

HeadConfig | None

The configuration of the head.

 None

lm_head

MaskedLMHeadConfig | None

The configuration of the masked language model head.

 None

add_cross_attention

bool

Whether to add cross-attention layers when the model is used as a decoder.

 False

Examples:

Python Console Session
1
2
3
4
5
6
7
>>> from multimolecule import DnaBertConfig, DnaBertModel
>>> # Initializing a DNABERT multimolecule/dnabert style configuration
>>> configuration = DnaBertConfig()
>>> # Initializing a model (with random weights) from the multimolecule/dnabert style configuration
>>> model = DnaBertModel(configuration)
>>> # Accessing the model configuration
>>> configuration = model.config
Source code in multimolecule/models/dnabert/configuration_dnabert.py
Python
 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
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
class DnaBertConfig(PreTrainedConfig):
    r"""
    This is the configuration class to store the configuration of a
    [`DnaBertModel`][multimolecule.models.DnaBertModel]. It is used to instantiate a DnaBert model according
    to the specified arguments, defining the model architecture. Instantiating a configuration with the defaults will
    yield a similar configuration to that of the DNABERT
    [zhihan1996/DNA_bert_6](https://huggingface.co/zhihan1996/DNA_bert_6) architecture.

    Configuration objects inherit from [`PreTrainedConfig`][multimolecule.models.PreTrainedConfig] and can be used to
    control the model outputs. Read the documentation from [`PreTrainedConfig`][multimolecule.models.PreTrainedConfig]
    for more information.

    Args:
        vocab_size:
            Vocabulary size of the DnaBert model. Defines the number of different tokens that can be represented by
            the `input_ids` passed when calling [`DnaBertModel`].
        hidden_size:
            Dimensionality of the encoder layers and the pooler layer.
        num_hidden_layers:
            Number of hidden layers in the Transformer encoder.
        num_attention_heads:
            Number of attention heads for each attention layer in the Transformer encoder.
        intermediate_size:
            Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer encoder.
        hidden_act:
            The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
            `"relu"`, `"silu"` and `"gelu_new"` are supported.
        hidden_dropout:
            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
        attention_dropout:
            The dropout ratio for the attention probabilities.
        max_position_embeddings:
            The maximum sequence length that this model might ever be used with. Typically set this to something large
            just in case (e.g., 512 or 1024 or 2048).
        initializer_range:
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        layer_norm_eps:
            The epsilon used by the layer normalization layers.
        position_embedding_type:
            Type of position embedding. Choose one of `"absolute"`, `"relative_key"`, `"relative_key_query"`. For
            positional embeddings use `"absolute"`. For more information on `"relative_key"`, please refer to
            [Self-Attention with Relative Position Representations (Shaw et al.)](https://arxiv.org/abs/1803.02155).
            For more information on `"relative_key_query"`, please refer to *Method 4* in [Improve Transformer Models
            with Better Relative Position Embeddings (Huang et al.)](https://arxiv.org/abs/2009.13658).
        is_decoder:
            Whether the model is used as a decoder or not. If `False`, the model is used as an encoder.
        use_cache:
            Whether or not the model should return the last key/values attentions (not used by all models). Only
            relevant if `config.is_decoder=True`.
        head:
            The configuration of the head.
        lm_head:
            The configuration of the masked language model head.
        add_cross_attention:
            Whether to add cross-attention layers when the model is used as a decoder.

    Examples:
        >>> from multimolecule import DnaBertConfig, DnaBertModel
        >>> # Initializing a DNABERT multimolecule/dnabert style configuration
        >>> configuration = DnaBertConfig()
        >>> # Initializing a model (with random weights) from the multimolecule/dnabert style configuration
        >>> model = DnaBertModel(configuration)
        >>> # Accessing the model configuration
        >>> configuration = model.config
    """

    model_type = "dnabert"

    def __init__(
        self,
        vocab_size: int = 4102,
        hidden_size: int = 768,
        num_hidden_layers: int = 12,
        num_attention_heads: int = 12,
        intermediate_size: int = 3072,
        hidden_act: str = "gelu",
        hidden_dropout: float = 0.1,
        attention_dropout: float = 0.1,
        max_position_embeddings: int = 512,
        initializer_range: float = 0.02,
        layer_norm_eps: float = 1e-12,
        position_embedding_type: str = "absolute",
        is_decoder: bool = False,
        use_cache: bool = True,
        head: HeadConfig | None = None,
        lm_head: MaskedLMHeadConfig | None = None,
        add_cross_attention: bool = False,
        **kwargs,
    ):
        super().__init__(**kwargs)
        validate_attention_dimensions(hidden_size, num_attention_heads)
        self.vocab_size = vocab_size
        self.type_vocab_size = 2
        self.hidden_size = hidden_size
        self.num_hidden_layers = num_hidden_layers
        self.num_attention_heads = num_attention_heads
        self.intermediate_size = intermediate_size
        self.hidden_act = hidden_act
        self.hidden_dropout = hidden_dropout
        self.attention_dropout = attention_dropout
        self.max_position_embeddings = max_position_embeddings
        self.initializer_range = initializer_range
        self.layer_norm_eps = layer_norm_eps
        self.position_embedding_type = position_embedding_type
        self.is_decoder = is_decoder
        self.use_cache = use_cache
        self.head = HeadConfig(**head) if head is not None else None
        self.lm_head = MaskedLMHeadConfig(**lm_head) if lm_head is not None else None
        self.add_cross_attention = add_cross_attention

DnaBertForContactPrediction

Bases: DnaBertPreTrainedModel

Examples:

Python Console Session
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
>>> import torch
>>> from multimolecule import DnaBertConfig, DnaBertForContactPrediction, DnaTokenizer
>>> config = DnaBertConfig()
>>> model = DnaBertForContactPrediction(config)
>>> tokenizer = DnaTokenizer.from_pretrained("multimolecule/dna")
>>> input = tokenizer("ACGTACGT", return_tensors="pt")
>>> output = model(**input, labels=torch.randint(2, (1, 8, 8)))
>>> output["logits"].shape
torch.Size([1, 8, 8, 1])
>>> output["loss"]
tensor(..., grad_fn=<BinaryCrossEntropyWithLogitsBackward0>)
Source code in multimolecule/models/dnabert/modeling_dnabert.py
Python
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
class DnaBertForContactPrediction(DnaBertPreTrainedModel):
    """
    Examples:
        >>> import torch
        >>> from multimolecule import DnaBertConfig, DnaBertForContactPrediction, DnaTokenizer
        >>> config = DnaBertConfig()
        >>> model = DnaBertForContactPrediction(config)
        >>> tokenizer = DnaTokenizer.from_pretrained("multimolecule/dna")
        >>> input = tokenizer("ACGTACGT", return_tensors="pt")
        >>> output = model(**input, labels=torch.randint(2, (1, 8, 8)))
        >>> output["logits"].shape
        torch.Size([1, 8, 8, 1])
        >>> output["loss"]  # doctest:+ELLIPSIS
        tensor(..., grad_fn=<BinaryCrossEntropyWithLogitsBackward0>)
    """

    def __init__(self, config: DnaBertConfig):
        super().__init__(config)
        self.model = DnaBertModel(config, add_pooling_layer=False)
        self.contact_head = ContactPredictionHead(config)
        self.head_config = self.contact_head.config
        self.require_attentions = self.contact_head.require_attentions

        # Initialize weights and apply final processing
        self.post_init()

    @can_return_tuple
    def forward(
        self,
        input_ids: Tensor | NestedTensor | None = None,
        attention_mask: Tensor | None = None,
        position_ids: Tensor | None = None,
        inputs_embeds: Tensor | NestedTensor | None = None,
        labels: Tensor | None = None,
        **kwargs: Unpack[TransformersKwargs],
    ) -> tuple[Tensor, ...] | ContactPredictorOutput:
        if self.require_attentions:
            output_attentions = kwargs.get("output_attentions", self.config.output_attentions)
            if output_attentions is False:
                warn("output_attentions must be True since prediction head requires attentions.")
            kwargs["output_attentions"] = True
        outputs = self.model(
            input_ids,
            attention_mask=attention_mask,
            position_ids=position_ids,
            inputs_embeds=inputs_embeds,
            return_dict=True,
            **kwargs,
        )

        output = self.contact_head(outputs, attention_mask, input_ids, labels)
        logits, loss = output.logits, output.loss

        return ContactPredictorOutput(
            loss=loss,
            logits=logits,
            hidden_states=outputs.hidden_states,
            attentions=outputs.attentions,
        )

DnaBertForMaskedLM

Bases: DnaBertPreTrainedModel

Examples:

Python Console Session
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
>>> import torch
>>> from multimolecule import DnaBertConfig, DnaBertForMaskedLM, DnaTokenizer
>>> config = DnaBertConfig()
>>> model = DnaBertForMaskedLM(config)
>>> tokenizer = DnaTokenizer.from_pretrained("multimolecule/dna")
>>> input = tokenizer("ACGTACGT", return_tensors="pt")
>>> output = model(**input, labels=input["input_ids"])
>>> output["logits"].shape
torch.Size([1, 10, 4102])
>>> output["loss"]
tensor(..., grad_fn=<NllLossBackward0>)
Source code in multimolecule/models/dnabert/modeling_dnabert.py
Python
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
class DnaBertForMaskedLM(DnaBertPreTrainedModel):
    """
    Examples:
        >>> import torch
        >>> from multimolecule import DnaBertConfig, DnaBertForMaskedLM, DnaTokenizer
        >>> config = DnaBertConfig()
        >>> model = DnaBertForMaskedLM(config)
        >>> tokenizer = DnaTokenizer.from_pretrained("multimolecule/dna")
        >>> input = tokenizer("ACGTACGT", return_tensors="pt")
        >>> output = model(**input, labels=input["input_ids"])
        >>> output["logits"].shape
        torch.Size([1, 10, 4102])
        >>> output["loss"]  # doctest:+ELLIPSIS
        tensor(..., grad_fn=<NllLossBackward0>)
    """

    _tied_weights_keys = {
        "lm_head.decoder.weight": "model.embeddings.word_embeddings.weight",
        "lm_head.decoder.bias": "lm_head.bias",
    }

    def __init__(self, config: DnaBertConfig):
        super().__init__(config)
        if config.is_decoder:
            warn(
                "If you want to use `DnaBertForMaskedLM` make sure `config.is_decoder=False` for "
                "bi-directional self-attention."
            )
        self.model = DnaBertModel(config, add_pooling_layer=False)
        self.lm_head = MaskedLMHead(config)

        # Initialize weights and apply final processing
        self.post_init()

    def get_output_embeddings(self):
        return self.lm_head.decoder

    def set_output_embeddings(self, embeddings):
        self.lm_head.decoder = embeddings
        if hasattr(self.lm_head, "bias"):
            self.lm_head.bias = embeddings.bias

    @can_return_tuple
    def forward(
        self,
        input_ids: Tensor | NestedTensor | None = None,
        attention_mask: Tensor | None = None,
        position_ids: Tensor | None = None,
        inputs_embeds: Tensor | NestedTensor | None = None,
        encoder_hidden_states: Tensor | None = None,
        encoder_attention_mask: Tensor | None = None,
        labels: Tensor | None = None,
        **kwargs: Unpack[TransformersKwargs],
    ) -> tuple[Tensor, ...] | MaskedLMOutput:
        outputs = self.model(
            input_ids,
            attention_mask=attention_mask,
            position_ids=position_ids,
            inputs_embeds=inputs_embeds,
            encoder_hidden_states=encoder_hidden_states,
            encoder_attention_mask=encoder_attention_mask,
            return_dict=True,
            **kwargs,
        )

        output = self.lm_head(outputs, labels)
        logits, loss = output.logits, output.loss

        return MaskedLMOutput(
            loss=loss,
            logits=logits,
            hidden_states=outputs.hidden_states,
            attentions=outputs.attentions,
        )

DnaBertForSequencePrediction

Bases: DnaBertPreTrainedModel

Examples:

Python Console Session
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
>>> import torch
>>> from multimolecule import DnaBertConfig, DnaBertForSequencePrediction, DnaTokenizer
>>> config = DnaBertConfig()
>>> model = DnaBertForSequencePrediction(config)
>>> tokenizer = DnaTokenizer.from_pretrained("multimolecule/dna")
>>> input = tokenizer("ACGTACGT", return_tensors="pt")
>>> output = model(**input, labels=torch.tensor([[1]]))
>>> output["logits"].shape
torch.Size([1, 1])
>>> output["loss"]
tensor(..., grad_fn=<BinaryCrossEntropyWithLogitsBackward0>)
Source code in multimolecule/models/dnabert/modeling_dnabert.py
Python
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
class DnaBertForSequencePrediction(DnaBertPreTrainedModel):
    """
    Examples:
        >>> import torch
        >>> from multimolecule import DnaBertConfig, DnaBertForSequencePrediction, DnaTokenizer
        >>> config = DnaBertConfig()
        >>> model = DnaBertForSequencePrediction(config)
        >>> tokenizer = DnaTokenizer.from_pretrained("multimolecule/dna")
        >>> input = tokenizer("ACGTACGT", return_tensors="pt")
        >>> output = model(**input, labels=torch.tensor([[1]]))
        >>> output["logits"].shape
        torch.Size([1, 1])
        >>> output["loss"]  # doctest:+ELLIPSIS
        tensor(..., grad_fn=<BinaryCrossEntropyWithLogitsBackward0>)
    """

    def __init__(self, config: DnaBertConfig):
        super().__init__(config)
        self.model = DnaBertModel(config)
        self.sequence_head = SequencePredictionHead(config)
        self.head_config = self.sequence_head.config

        # Initialize weights and apply final processing
        self.post_init()

    @can_return_tuple
    def forward(
        self,
        input_ids: Tensor | NestedTensor | None = None,
        attention_mask: Tensor | None = None,
        position_ids: Tensor | None = None,
        inputs_embeds: Tensor | NestedTensor | None = None,
        labels: Tensor | None = None,
        **kwargs: Unpack[TransformersKwargs],
    ) -> tuple[Tensor, ...] | SequencePredictorOutput:
        outputs = self.model(
            input_ids,
            attention_mask=attention_mask,
            position_ids=position_ids,
            inputs_embeds=inputs_embeds,
            return_dict=True,
            **kwargs,
        )

        output = self.sequence_head(outputs, labels)
        logits, loss = output.logits, output.loss

        return SequencePredictorOutput(
            loss=loss,
            logits=logits,
            hidden_states=outputs.hidden_states,
            attentions=outputs.attentions,
        )

DnaBertForTokenPrediction

Bases: DnaBertPreTrainedModel

Examples:

Python Console Session
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
>>> import torch
>>> from multimolecule import DnaBertConfig, DnaBertForTokenPrediction, DnaTokenizer
>>> config = DnaBertConfig()
>>> model = DnaBertForTokenPrediction(config)
>>> tokenizer = DnaTokenizer.from_pretrained("multimolecule/dna")
>>> input = tokenizer("ACGTACGT", return_tensors="pt")
>>> output = model(**input, labels=torch.randint(2, (1, 8)))
>>> output["logits"].shape
torch.Size([1, 8, 1])
>>> output["loss"]
tensor(..., grad_fn=<BinaryCrossEntropyWithLogitsBackward0>)
Source code in multimolecule/models/dnabert/modeling_dnabert.py
Python
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
class DnaBertForTokenPrediction(DnaBertPreTrainedModel):
    """
    Examples:
        >>> import torch
        >>> from multimolecule import DnaBertConfig, DnaBertForTokenPrediction, DnaTokenizer
        >>> config = DnaBertConfig()
        >>> model = DnaBertForTokenPrediction(config)
        >>> tokenizer = DnaTokenizer.from_pretrained("multimolecule/dna")
        >>> input = tokenizer("ACGTACGT", return_tensors="pt")
        >>> output = model(**input, labels=torch.randint(2, (1, 8)))
        >>> output["logits"].shape
        torch.Size([1, 8, 1])
        >>> output["loss"]  # doctest:+ELLIPSIS
        tensor(..., grad_fn=<BinaryCrossEntropyWithLogitsBackward0>)
    """

    def __init__(self, config: DnaBertConfig):
        super().__init__(config)
        self.model = DnaBertModel(config, add_pooling_layer=False)
        self.token_head = TokenPredictionHead(config)
        self.head_config = self.token_head.config

        # Initialize weights and apply final processing
        self.post_init()

    @can_return_tuple
    def forward(
        self,
        input_ids: Tensor | NestedTensor | None = None,
        attention_mask: Tensor | None = None,
        position_ids: Tensor | None = None,
        inputs_embeds: Tensor | NestedTensor | None = None,
        labels: Tensor | None = None,
        **kwargs: Unpack[TransformersKwargs],
    ) -> tuple[Tensor, ...] | TokenPredictorOutput:
        outputs = self.model(
            input_ids,
            attention_mask=attention_mask,
            position_ids=position_ids,
            inputs_embeds=inputs_embeds,
            return_dict=True,
            **kwargs,
        )

        output = self.token_head(outputs, attention_mask, input_ids, labels)
        logits, loss = output.logits, output.loss

        return TokenPredictorOutput(
            loss=loss,
            logits=logits,
            hidden_states=outputs.hidden_states,
            attentions=outputs.attentions,
        )

DnaBertModel

Bases: DnaBertPreTrainedModel

Examples:

Python Console Session
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
>>> import torch
>>> from multimolecule import DnaBertConfig, DnaBertModel, DnaTokenizer
>>> config = DnaBertConfig()
>>> model = DnaBertModel(config)
>>> tokenizer = DnaTokenizer.from_pretrained("multimolecule/dna")
>>> input = tokenizer("ACGTACGT", return_tensors="pt")
>>> output = model(**input)
>>> output["last_hidden_state"].shape
torch.Size([1, 10, 768])
>>> output["pooler_output"].shape
torch.Size([1, 768])
Source code in multimolecule/models/dnabert/modeling_dnabert.py
Python
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
class DnaBertModel(DnaBertPreTrainedModel):
    """
    Examples:
        >>> import torch
        >>> from multimolecule import DnaBertConfig, DnaBertModel, DnaTokenizer
        >>> config = DnaBertConfig()
        >>> model = DnaBertModel(config)
        >>> tokenizer = DnaTokenizer.from_pretrained("multimolecule/dna")
        >>> input = tokenizer("ACGTACGT", return_tensors="pt")
        >>> output = model(**input)
        >>> output["last_hidden_state"].shape
        torch.Size([1, 10, 768])
        >>> output["pooler_output"].shape
        torch.Size([1, 768])
    """

    def __init__(self, config: DnaBertConfig, add_pooling_layer: bool = True):
        super().__init__(config)
        self.pad_token_id = config.pad_token_id
        self.gradient_checkpointing = False
        self.embeddings = DnaBertEmbeddings(config)
        self.encoder = DnaBertEncoder(config)
        self.pooler = DnaBertPooler(config) if add_pooling_layer else None

        # Initialize weights and apply final processing
        self.post_init()

    def get_input_embeddings(self):
        return self.embeddings.word_embeddings

    def set_input_embeddings(self, value):
        self.embeddings.word_embeddings = value

    @merge_with_config_defaults
    @capture_outputs
    def forward(
        self,
        input_ids: Tensor | NestedTensor | None = None,
        attention_mask: Tensor | None = None,
        position_ids: Tensor | None = None,
        inputs_embeds: Tensor | NestedTensor | None = None,
        encoder_hidden_states: Tensor | None = None,
        encoder_attention_mask: Tensor | None = None,
        past_key_values: Cache | None = None,
        use_cache: bool | None = None,
        cache_position: Tensor | None = None,
        **kwargs: Unpack[TransformersKwargs],
    ) -> tuple[Tensor, ...] | BaseModelOutputWithPoolingAndCrossAttentions:
        r"""
        Args:
            encoder_hidden_states:
                Shape: `(batch_size, sequence_length, hidden_size)`

                Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if
                the model is configured as a decoder.
            encoder_attention_mask:
                Shape: `(batch_size, sequence_length)`

                Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used
                in the cross-attention if the model is configured as a decoder. Mask values selected in `[0, 1]`:

                - 1 for tokens that are **not masked**,
                - 0 for tokens that are **masked**.
            past_key_values:
                Tuple of length `config.n_layers` with each tuple having 4 tensors of shape
                `(batch_size, num_heads, sequence_length - 1, embed_size_per_head)

                Contains precomputed key and value hidden states of the attention blocks. Can be used to speed up
                decoding.

                If `past_key_values` are used, the user can optionally input only the last `decoder_input_ids` (those
                that don't have their past key value states given to this model) of shape `(batch_size, 1)` instead of
                all `decoder_input_ids` of shape `(batch_size, sequence_length)`.
            use_cache:
                If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding
                (see `past_key_values`).
        """
        if self.config.is_decoder:
            use_cache = use_cache if use_cache is not None else self.config.use_cache
        else:
            use_cache = False
        if use_cache and past_key_values is None:
            past_key_values = (
                EncoderDecoderCache(DynamicCache(config=self.config), DynamicCache(config=self.config))
                if encoder_hidden_states is not None or self.config.is_encoder_decoder
                else DynamicCache(config=self.config)
            )

        if isinstance(input_ids, NestedTensor) and attention_mask is None:
            attention_mask = input_ids.mask
        if (input_ids is None) ^ (inputs_embeds is not None):
            raise ValueError("You must specify exactly one of input_ids or inputs_embeds")
        if input_ids is not None:
            device = input_ids.device
            seq_length = input_ids.shape[1]
        else:
            device = inputs_embeds.device  # type: ignore[union-attr]
            seq_length = inputs_embeds.shape[1]  # type: ignore[union-attr]

        # past_key_values_length
        past_key_values_length = past_key_values.get_seq_length() if past_key_values is not None else 0
        if cache_position is None:
            cache_position = torch.arange(past_key_values_length, past_key_values_length + seq_length, device=device)

        if attention_mask is None and input_ids is not None and self.pad_token_id is not None:
            attention_mask = input_ids.ne(self.pad_token_id)

        embedding_output = self.embeddings(
            input_ids=input_ids,
            position_ids=position_ids,
            inputs_embeds=inputs_embeds,
            past_key_values_length=past_key_values_length,
        )
        attention_mask, encoder_attention_mask = self._create_attention_masks(
            attention_mask=attention_mask,
            encoder_attention_mask=encoder_attention_mask,
            embedding_output=embedding_output,
            encoder_hidden_states=encoder_hidden_states,
            cache_position=cache_position,
            past_key_values=past_key_values,
        )
        encoder_outputs = self.encoder(
            embedding_output,
            attention_mask,
            encoder_hidden_states,
            encoder_attention_mask=encoder_attention_mask,
            past_key_values=past_key_values,
            use_cache=use_cache,
            cache_position=cache_position,
            position_ids=position_ids,
            **kwargs,
        )
        sequence_output = encoder_outputs.last_hidden_state
        pooled_output = self.pooler(sequence_output) if self.pooler is not None else None

        return BaseModelOutputWithPoolingAndCrossAttentions(
            last_hidden_state=sequence_output,
            pooler_output=pooled_output,
            past_key_values=encoder_outputs.past_key_values,
        )

    def _create_attention_masks(
        self,
        attention_mask,
        encoder_attention_mask,
        embedding_output,
        encoder_hidden_states,
        cache_position,
        past_key_values,
    ):
        if self.config.is_decoder:
            attention_mask = create_causal_mask(
                config=self.config,
                inputs_embeds=embedding_output,
                attention_mask=attention_mask,
                cache_position=cache_position,
                past_key_values=past_key_values,
            )
        else:
            attention_mask = create_bidirectional_mask(
                config=self.config, inputs_embeds=embedding_output, attention_mask=attention_mask
            )

        if encoder_attention_mask is not None:
            encoder_attention_mask = create_bidirectional_mask(
                config=self.config,
                inputs_embeds=embedding_output,
                attention_mask=encoder_attention_mask,
                encoder_hidden_states=encoder_hidden_states,
            )

        return attention_mask, encoder_attention_mask

forward

Python
forward(
    input_ids: Tensor | NestedTensor | None = None,
    attention_mask: Tensor | None = None,
    position_ids: Tensor | None = None,
    inputs_embeds: Tensor | NestedTensor | None = None,
    encoder_hidden_states: Tensor | None = None,
    encoder_attention_mask: Tensor | None = None,
    past_key_values: Cache | None = None,
    use_cache: bool | None = None,
    cache_position: Tensor | None = None,
    **kwargs: Unpack[TransformersKwargs]
) -> (
    tuple[Tensor, ...]
    | BaseModelOutputWithPoolingAndCrossAttentions
)

Parameters:

Name Type Description Default
encoder_hidden_states
Tensor | None

Shape: (batch_size, sequence_length, hidden_size)

Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if the model is configured as a decoder.

 None
encoder_attention_mask
Tensor | None

Shape: (batch_size, sequence_length)

Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used in the cross-attention if the model is configured as a decoder. Mask values selected in [0, 1]:

  • 1 for tokens that are not masked,
  • 0 for tokens that are masked.
 None
past_key_values
Cache | None

Tuple of length config.n_layers with each tuple having 4 tensors of shape `(batch_size, num_heads, sequence_length - 1, embed_size_per_head)

Contains precomputed key and value hidden states of the attention blocks. Can be used to speed up decoding.

If past_key_values are used, the user can optionally input only the last decoder_input_ids (those that don’t have their past key value states given to this model) of shape (batch_size, 1) instead of all decoder_input_ids of shape (batch_size, sequence_length).

 None
use_cache
bool | None

If set to True, past_key_values key value states are returned and can be used to speed up decoding (see past_key_values).

 None
Source code in multimolecule/models/dnabert/modeling_dnabert.py
Python
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
@merge_with_config_defaults
@capture_outputs
def forward(
    self,
    input_ids: Tensor | NestedTensor | None = None,
    attention_mask: Tensor | None = None,
    position_ids: Tensor | None = None,
    inputs_embeds: Tensor | NestedTensor | None = None,
    encoder_hidden_states: Tensor | None = None,
    encoder_attention_mask: Tensor | None = None,
    past_key_values: Cache | None = None,
    use_cache: bool | None = None,
    cache_position: Tensor | None = None,
    **kwargs: Unpack[TransformersKwargs],
) -> tuple[Tensor, ...] | BaseModelOutputWithPoolingAndCrossAttentions:
    r"""
    Args:
        encoder_hidden_states:
            Shape: `(batch_size, sequence_length, hidden_size)`

            Sequence of hidden-states at the output of the last layer of the encoder. Used in the cross-attention if
            the model is configured as a decoder.
        encoder_attention_mask:
            Shape: `(batch_size, sequence_length)`

            Mask to avoid performing attention on the padding token indices of the encoder input. This mask is used
            in the cross-attention if the model is configured as a decoder. Mask values selected in `[0, 1]`:

            - 1 for tokens that are **not masked**,
            - 0 for tokens that are **masked**.
        past_key_values:
            Tuple of length `config.n_layers` with each tuple having 4 tensors of shape
            `(batch_size, num_heads, sequence_length - 1, embed_size_per_head)

            Contains precomputed key and value hidden states of the attention blocks. Can be used to speed up
            decoding.

            If `past_key_values` are used, the user can optionally input only the last `decoder_input_ids` (those
            that don't have their past key value states given to this model) of shape `(batch_size, 1)` instead of
            all `decoder_input_ids` of shape `(batch_size, sequence_length)`.
        use_cache:
            If set to `True`, `past_key_values` key value states are returned and can be used to speed up decoding
            (see `past_key_values`).
    """
    if self.config.is_decoder:
        use_cache = use_cache if use_cache is not None else self.config.use_cache
    else:
        use_cache = False
    if use_cache and past_key_values is None:
        past_key_values = (
            EncoderDecoderCache(DynamicCache(config=self.config), DynamicCache(config=self.config))
            if encoder_hidden_states is not None or self.config.is_encoder_decoder
            else DynamicCache(config=self.config)
        )

    if isinstance(input_ids, NestedTensor) and attention_mask is None:
        attention_mask = input_ids.mask
    if (input_ids is None) ^ (inputs_embeds is not None):
        raise ValueError("You must specify exactly one of input_ids or inputs_embeds")
    if input_ids is not None:
        device = input_ids.device
        seq_length = input_ids.shape[1]
    else:
        device = inputs_embeds.device  # type: ignore[union-attr]
        seq_length = inputs_embeds.shape[1]  # type: ignore[union-attr]

    # past_key_values_length
    past_key_values_length = past_key_values.get_seq_length() if past_key_values is not None else 0
    if cache_position is None:
        cache_position = torch.arange(past_key_values_length, past_key_values_length + seq_length, device=device)

    if attention_mask is None and input_ids is not None and self.pad_token_id is not None:
        attention_mask = input_ids.ne(self.pad_token_id)

    embedding_output = self.embeddings(
        input_ids=input_ids,
        position_ids=position_ids,
        inputs_embeds=inputs_embeds,
        past_key_values_length=past_key_values_length,
    )
    attention_mask, encoder_attention_mask = self._create_attention_masks(
        attention_mask=attention_mask,
        encoder_attention_mask=encoder_attention_mask,
        embedding_output=embedding_output,
        encoder_hidden_states=encoder_hidden_states,
        cache_position=cache_position,
        past_key_values=past_key_values,
    )
    encoder_outputs = self.encoder(
        embedding_output,
        attention_mask,
        encoder_hidden_states,
        encoder_attention_mask=encoder_attention_mask,
        past_key_values=past_key_values,
        use_cache=use_cache,
        cache_position=cache_position,
        position_ids=position_ids,
        **kwargs,
    )
    sequence_output = encoder_outputs.last_hidden_state
    pooled_output = self.pooler(sequence_output) if self.pooler is not None else None

    return BaseModelOutputWithPoolingAndCrossAttentions(
        last_hidden_state=sequence_output,
        pooler_output=pooled_output,
        past_key_values=encoder_outputs.past_key_values,
    )

DnaBertPreTrainedModel

Bases: PreTrainedModel

An abstract class to handle weights initialization and a simple interface for downloading and loading pretrained models.

Source code in multimolecule/models/dnabert/modeling_dnabert.py
Python
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
class DnaBertPreTrainedModel(PreTrainedModel):
    """
    An abstract class to handle weights initialization and a simple interface for downloading and loading pretrained
    models.
    """

    config_class = DnaBertConfig
    base_model_prefix = "model"
    supports_gradient_checkpointing = True
    _supports_flash_attn = True
    _supports_sdpa = True
    _supports_flex_attn = True
    _supports_attention_backend = True
    _can_record_outputs: dict[str, Any] | None = None
    _no_split_modules = ["DnaBertLayer", "DnaBertEmbeddings"]

    @torch.no_grad()
    def _init_weights(self, module: nn.Module):
        super()._init_weights(module)
        if isinstance(module, DnaBertEmbeddings):
            # `position_ids` is a non-persistent buffer; under transformers v5 meta-init it
            # stays on the meta device after `from_pretrained`, so populate it here.
            init.copy_(module.position_ids, torch.arange(module.position_ids.shape[-1]).expand((1, -1)))