---
tags:
  - pytorch
  - safetensors
license: mit
---
 
# dm_qwen4b_emulator
 
2-layer MLP.
 
## Config
- `input_dim`: 6
- `hidden_dim`: 256
- `output_dim`: 3
 
## Usage
 
```python
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, output_dim),
        )
    def forward(self, x):
        return self.mlp(x)
 
path = hf_hub_download("chewwt/dm_qwen4b_emulator", "model.safetensors")
model = MLP(input_dim=6, hidden_dim=256, output_dim=3)
model.load_state_dict(load_file(path))
model.eval()
 
with torch.no_grad():
    out = model(torch.randn(1, 6))
```