# helia_edge.export.fp16

Rewrite a weight-only float16 TFLite model into a native float16 graph.

## helia_edge.export.fp16.to_native_fp16

`function` · `python`

```python
to_native_fp16(model_content: bytes) -> bytes
```

Return a graph whose inputs, weights, activations and outputs are FLOAT16.

The TFLite float16 optimization stores weights as FLOAT16 behind
``DEQUANTIZE`` operators and computes in FLOAT32. This drops each
FLOAT16 -> FLOAT32 ``DEQUANTIZE``, rewires its consumers to the FLOAT16
source, and converts every remaining FLOAT32 tensor and constant buffer to
FLOAT16. Constants outside the float16 range saturate to +/-65504, as in
TFLite's float16 optimization. Non-float tensors are unchanged. The dropped
``DEQUANTIZE`` outputs and operator codes no operator uses are removed, and
operator, subgraph and signature tensor indices are renumbered to match.
Buffers of removed tensors stay in the model; they are empty.

**Parameters**

| Name | Type | Default | Description |
| --- | --- | --- | --- |
| model_content | bytes | Required | Weight-only float16 TFLite flatbuffer. |

**Returns**

| Name | Type | Description |
| --- | --- | --- |
| bytes | bytes | Native float16 TFLite flatbuffer. |

Source: `helia_edge/export/fp16.py:13`