hpo_qwen8b_emulator

MLP with 3 hidden Linear->LayerNorm->ReLU block(s) and a linear output head.

Config

• input_dim: 11
• hidden_dim: 1024
• output_dim: 1
• n_layers: 3

Usage

import torch
import torch.nn as nn
from safetensors.torch import load_file
from huggingface_hub import hf_hub_download
 
class MLP(nn.Module):
    def __init__(self, input_dim, hidden_dim, output_dim):
        super().__init__()
        self.mlp = nn.Sequential(
            nn.Linear(input_dim, hidden_dim),
            nn.LayerNorm(hidden_dim),
            nn.ReLU(),
            nn.Linear(hidden_dim, hidden_dim),
            nn.LayerNorm(hidden_dim),
            nn.ReLU(),
            nn.Linear(hidden_dim, hidden_dim),
            nn.LayerNorm(hidden_dim),
            nn.ReLU(),
            nn.Linear(hidden_dim, output_dim),
        )
    def forward(self, x):
        return self.mlp(x)
 
path = hf_hub_download("chewwt/hpo_qwen8b_emulator", "model.safetensors")
model = MLP(input_dim=11, hidden_dim=1024, output_dim=1)
model.load_state_dict(load_file(path))
model.eval()
 
with torch.no_grad():
    out = model(torch.randn(1, 11))