evo_model.py

import torch
import torch.nn as nn
import torch.nn.functional as F

class EvoEncoder(nn.Module):
    def __init__(self, d_model=384, nhead=6, dim_feedforward=1024, num_layers=6):
        super().__init__()
        self.embedding = nn.Embedding(30522, d_model)  # BERT-base vocab size
        encoder_layer = nn.TransformerEncoderLayer(
            d_model=d_model,
            nhead=nhead,
            dim_feedforward=dim_feedforward,
            batch_first=True,
        )
        self.transformer = nn.TransformerEncoder(encoder_layer, num_layers=num_layers)
        self.memory_proj = nn.Linear(d_model, d_model)

    def forward(self, input_ids):
        x = self.embedding(input_ids)
        x = self.transformer(x)
        x = x.mean(dim=1)
        return self.memory_proj(x)

class EvoTransformer(nn.Module):
    def __init__(self, d_model=384):
        super().__init__()
        self.encoder = EvoEncoder(d_model=d_model)
        self.classifier = nn.Linear(d_model, 2)

    def forward(self, input_ids):
        x = self.encoder(input_ids)
        return x