Upload DNAEncoder

README.md

@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

config.json

@@ -0,0 +1,21 @@
+{
+  "activation": "gelu",
+  "architectures": [
+    "DNAEncoder"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_dna2vec.DNAEncoderConfig",
+    "AutoModel": "modeling_dna2vec.DNAEncoder"
+  },
+  "dim_feedforward": 1536,
+  "dropout": 0.1,
+  "embedding_dim": 1020,
+  "max_position_embeddings": 1024,
+  "model_type": "dna_encoder",
+  "num_heads": 12,
+  "num_layers": 6,
+  "pos_embedding": "SinusoidalPositionalEncoding",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "vocab_size": 10004
+}

configuration_dna2vec.py

@@ -0,0 +1,30 @@
+from transformers import PretrainedConfig
+from typing import Literal, Optional
+
+class DNAEncoderConfig(PretrainedConfig):
+    model_type = "dna_encoder"
+    
+    def __init__(
+        self,
+        vocab_size: int = 4,
+        embedding_dim: int = 384,
+        dim_feedforward: int = 1536,
+        num_heads: int = 12,
+        num_layers: int = 6,
+        dropout: float = 0.1,
+        activation: Literal["relu", "gelu"] = "gelu",
+        pos_embedding: Optional[str] = "SinusoidalPositionalEncoding",
+        max_position_embeddings: int = 1024,
+        **kwargs
+    ):
+        self.vocab_size = vocab_size
+        self.embedding_dim = embedding_dim
+        self.dim_feedforward = dim_feedforward
+        self.num_heads = num_heads
+        self.num_layers = num_layers
+        self.dropout = dropout
+        self.activation = activation
+        self.pos_embedding = pos_embedding
+        self.max_position_embeddings = max_position_embeddings
+        
+        super().__init__(**kwargs)

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:629788c307b5ea728313d9beedae989568aeed4fc50ced7901de4f1cabecce56
+size 220341040

modeling_dna2vec.py

@@ -0,0 +1,108 @@
+from .configuration_dna2vec import DNAEncoderConfig
+from transformers import PreTrainedModel
+import math
+from typing import Literal, Optional
+import torch
+import torch.nn as nn
+
+class Encoder(nn.Module):
+    def __init__(
+        self,
+        vocab_size: int = 4,
+        embedding_dim: int = 384,
+        dim_feedforward: int = 1536,
+        num_heads: int = 12,
+        num_layers: int = 6,
+        dropout: float = 0.1,
+        activation: Literal["relu", "gelu"] = "gelu",
+        pos_embedding: Optional[str] = "SinusoidalPositionalEncoding",
+        max_position_embeddings: int = 1024,
+    ):
+        """
+        Default values taken from miniLM v6
+        https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2/blob/main/config.json
+        """
+        super().__init__()
+        self.vocab_size = vocab_size
+        self.embedding_dim = embedding_dim
+        self.dropout = dropout
+        self.num_heads = num_heads
+        self.num_layers = num_layers
+        self.emb_dropout = nn.Dropout(p=dropout)
+        
+        if pos_embedding == "SinusoidalPositionalEncoding":
+            position = torch.arange(max_position_embeddings).unsqueeze(1)
+            div_term = torch.exp(
+                torch.arange(0, embedding_dim, 2) * (-math.log(10000.0) / embedding_dim)
+            )
+            pe = torch.zeros(max_position_embeddings, 1, embedding_dim)
+            pe[:, 0, 0::2] = torch.sin(position * div_term)
+            pe[:, 0, 1::2] = torch.cos(position * div_term)
+            pe = pe.squeeze(1).unsqueeze(0)
+            self.register_buffer("positional_embedding", pe)
+        else:
+            raise ValueError(f"Positional embedding {pos_embedding} not found")
+
+        self.embedding = nn.Embedding(
+            num_embeddings=vocab_size,
+            embedding_dim=embedding_dim,
+        )
+
+        # create encode layers
+        encoder_layer = nn.TransformerEncoderLayer(
+            d_model=embedding_dim,
+            nhead=num_heads,
+            dim_feedforward=dim_feedforward,
+            dropout=dropout,
+            activation=activation,
+            batch_first=True,
+            norm_first=True,  # following: https://arxiv.org/pdf/2002.04745.pdf
+        )
+        self.trf_encoder = nn.TransformerEncoder(
+            encoder_layer=encoder_layer, num_layers=num_layers
+        )
+
+    def forward(
+        self, input_ids: torch.Tensor, attention_mask: Optional[torch.Tensor] = None
+    ) -> torch.Tensor:
+        # input_ids.names = ["batch", "sequence"]
+        # embedding does not support named tensors
+
+        # Embed
+        emb = self.emb_dropout(
+            self.embedding(input_ids) + self.positional_embedding[:, :input_ids.size(1), :]
+        )
+        # emb.names = ["batch", "sequence", "embedding"]
+
+        # Contextualize embeddings
+        attn = None
+        if attention_mask is not None:
+            attn = attention_mask == 0  # to boolean
+        out = self.trf_encoder(emb, src_key_padding_mask=attn)
+        # out.names = ["batch", "sequence", "embedding"]
+        return out
+
+class DNAEncoder(PreTrainedModel):
+    config_class = DNAEncoderConfig
+    
+    def __init__(self, config: DNAEncoderConfig):
+        super().__init__(config)
+        self.config = config
+        self.encoder =  Encoder(
+            vocab_size=config.vocab_size,
+            embedding_dim=config.embedding_dim,
+            dim_feedforward=config.dim_feedforward,
+            num_heads=config.num_heads,
+            num_layers=config.num_layers,
+            dropout=config.dropout,
+            activation=config.activation,
+            max_position_embeddings=config.max_position_embeddings,
+        )
+            
+    def forward(
+        self,
+        input_ids: torch.Tensor,
+        attention_mask: Optional[torch.Tensor] = None,
+        **kwargs,
+    ) -> torch.Tensor:
+        return self.encoder(input_ids, attention_mask)