GGUF
vokra
hubert-large-ls960 / SOURCE.md
ayousanz's picture
Upload folder using huggingface_hub
fd95a67 verified
|
Raw
History Blame Contribute Delete
776 Bytes

Provenance — vokra/hubert-large-ls960

Field Value
Upstream source facebook/hubert-large-ls960-ft (Meta HuBERT-Large 317M CTC LibriSpeech 960h, apache-2.0)
Upstream licence apache-2.0
Architecture hubert
Tensors 424
SHA-256 e9e1538412e165cb47b81aaa2fd046cea1fa7fd9dd71078e11bdedc3dd2c18a2
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

vokra-cli convert --model <kind> --input <upstream> --output model.gguf
shasum -a 256 model.gguf   # expect e9e1538412e165cb47b81aaa2fd046cea1fa7fd9dd71078e11bdedc3dd2c18a2