ONNX Model Export
Generated: 2025-12-28T17:48:01.525Z
Model: micro-distill-grpo-vae
Framework: PyTorch 2.0+
ONNX Version: 1.14.0

Graph Structure:
- Inputs:
  - input_ids: int64[batch_size, sequence_length]
  - attention_mask: int64[batch_size, sequence_length]
  - position_ids: int64[batch_size, sequence_length] (optional)

- Outputs:
  - logits: float32[batch_size, sequence_length, 50257]

Layers:
  - Embedding: 512 dimensions
  - 8 Transformer blocks
  - Layer normalization
  - Language modeling head

Optimizations:
  - Constant folding: enabled
  - Shape inference: enabled
  - Dynamic axes: sequence_length
  - Opset: 17
  - IR version: 9

Quantization: Q4 (4-bit)