# Provenance — vokra/moss-audio-4b-instruct

| Field | Value |
|---|---|
| Upstream source | OpenMOSS-Team/MOSS-Audio-4B-Instruct (configuration_moss_audio.py custom-code audio-LLM, apache-2.0; placeholder axes = Local family) |
| Upstream licence | `apache-2.0` |
| Architecture | `moss_tts` |
| Tensors | 901 |
| SHA-256 | `02b1af053f3dcdf18e78d59e1fcc2dc57a134b10dd6b04a4e3212f8a9ebf7b62` |
| Converted by | vokra-core 0.1.0-alpha.0 |
| GGUF schema generation | 1 |

Every row is read from the artifact's own `vokra.*` metadata; none of it
is supplied by hand, so this file cannot disagree with the weight it
describes.

## Reproducing

```bash
vokra-cli convert --model <kind> --input <upstream> --output model.gguf
shasum -a 256 model.gguf   # expect 02b1af053f3dcdf18e78d59e1fcc2dc57a134b10dd6b04a4e3212f8a9ebf7b62
```