swift-ministral-8b-deepscaler

import torch
import torch.nn as nn

class LinearRewardModel(nn.Module):
    def __init__(self, feature_dim, disable_gate=False):
        super(LinearRewardModel, self).__init__()
        self.disable_gate = disable_gate
        if not disable_gate:
            self.fused_layer = nn.Linear(feature_dim, 2)
        else:
            self.reward_layer = nn.Linear(feature_dim, 1)

    def forward(self, x):
        # ... logic ...
        pass

model = LinearRewardModel(feature_dim=151552, disable_gate=False)
sd = torch.load("swift_reward_model.pt")
model.load_state_dict(sd)