---
license: apache-2.0
library_name: libreyolo
pipeline_tag: image-segmentation
base_model: feyninc/FeyNobg
base_model_relation: quantized
tags:
  - background-removal
  - matte
  - dichotomous-image-segmentation
  - feynobg
  - birefnet
  - fp8
  - quantized
  - libreyolo
---

# LibreFeyNobgl-matte-fp8

FeyNobg background removal, repackaged for LibreYOLO's `matte` task. Predicts
a soft alpha matte at a fixed native 1024x1024.

This repo hosts the **fp8 (E4M3 weights, calibrated static scales, fp16 remainder; on Ada/Hopper/Blackwell GPUs the Linear layers execute natively on the fp8 tensor cores via torch._scaled_mm, matching the fp16 checkpoint's speed at half its size - pass cuda_graph=True to predict for the full effect)** post-training-quantized variant. The default-precision weights auto-download; quantized variants are opt-in: download the `.pt` and pass its path as the weights argument (the checkpoint's `quant` manifest rebuilds the quantized structure at load time).

```python
from libreyolo import LibreYOLO

m = LibreYOLO("LibreFeyNobgl-matte-fp8.pt")
res = m.predict("product.jpg")
res[0].matte            # (H, W) float alpha in [0, 1]
res[0].save("cut.png")  # transparent-background PNG
```

## Source

Derived from [feyninc/FeyNobg](https://huggingface.co/feyninc/FeyNobg)
([nobg library](https://github.com/feyninc/nobg)), Apache-2.0,
Copyright (c) 2026 Feyn Inc. FeyNobg builds on
[ZhengPeng7/BiRefNet](https://github.com/ZhengPeng7/BiRefNet) (MIT,
Copyright (c) 2024 ZhengPeng).

Backbone: Swin Transformer v1, Swin-L tier with stage 3 deepened from 18 to
24 blocks (263M parameters). Training data provenance (upstream): not
disclosed by Feyn Inc.; this repo redistributes the author's released
weights under their Apache-2.0 grant and does not redistribute training data.

## Modifications

State-dict metadata-wrap into the LibreYOLO v1.0 checkpoint schema, then
post-training quantization with LibreYOLO's `quantize` API
(fp8 (E4M3 weights, calibrated static scales, fp16 remainder; on Ada/Hopper/Blackwell GPUs the Linear layers execute natively on the fp8 tensor cores via torch._scaled_mm, matching the fp16 checkpoint's speed at half its size - pass cuda_graph=True to predict for the full effect)), stored in the packed finalized format documented in
`docs/quantization.md` and `docs/checkpoint_schema.md` of the
[LibreYOLO source repository](https://github.com/LibreYOLO/libreyolo).

## License

Apache License 2.0. See the [`LICENSE`](./LICENSE) and [`NOTICE`](./NOTICE) files.