qwen2-audio-7b-instruct (Vokra GGUF)

Converted to the Vokra GGUF format for Vokra, a zero-dependency speech-AI inference runtime.

This is a conversion, not a new model. The weights are the upstream ones; Vokra re-packages them so its runtime can memory-map them directly. Credit for the model belongs upstream — see Source below.

Files

File	Size	SHA-256
qwen2-audio.gguf	16016.3 MB	c101cb8d48c1c9dcecefe7cd71e96e31fd1d831bb6b49aabc9fdc7e5505edbb7

Usage

# Download (any HTTP client works — the file is a plain GGUF)
curl -L -o qwen2-audio.gguf \
  https://huggingface.co/vokra/qwen2-audio-7b-instruct/resolve/main/qwen2-audio.gguf

vokra-cli run --model qwen2-audio.gguf --input input.wav

Provenance

Field	Value
Architecture	qwen2_audio
Tensors	876
Upstream source	Qwen/Qwen2-Audio-7B-Instruct (Alibaba 7B Whisper+Qwen2 audio-LLM, apache-2.0)
Upstream licence	apache-2.0
Licence class	permissive
Registry model id	qwen2-audio-7b-instruct
Vokra GGUF schema	1
Converted by	vokra-core 0.1.0-alpha.0

Every row above is read out of this file's own vokra.* metadata, so the card cannot claim something the artifact does not carry.

Licence

The weights are distributed under apache-2.0, unchanged from upstream. Conversion does not alter the licence, and your obligations run to the upstream author.

Verifying this file

shasum -a 256 qwen2-audio.gguf
# expect: c101cb8d48c1c9dcecefe7cd71e96e31fd1d831bb6b49aabc9fdc7e5505edbb7