kimi-audio / SOURCE.md
ayousanz's picture
Upload folder using huggingface_hub
a9d3c39 verified
|
Raw
History Blame Contribute Delete
710 Bytes
# Provenance — vokra/kimi-audio
| Field | Value |
|---|---|
| Upstream source | moonshotai/Kimi-Audio-7B-Instruct |
| Upstream licence | `mit` |
| Architecture | `kimi_audio` |
| Tensors | 453 |
| SHA-256 | `1251467c92039f473772babe0b0f1f79fab5fbbe35ff5a22d603f50fe0c497bd` |
| 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 1251467c92039f473772babe0b0f1f79fab5fbbe35ff5a22d603f50fe0c497bd
```