compressed_model.pt: serialized PyTorch model with custom CompressedLinear modules
compression_metadata.json: metadata describing the compression setup

Important

This is not a standard Hugging Face from_pretrained() checkpoint. Loading this artifact requires the custom Python code defining the CompressedLinear module and codec pipeline used during export.

Base model

Qwen/Qwen2-Audio-7B-Instruct

Notes

This artifact was produced for compression experiments on English -> Chinese speech translation.

alonsopg/qwen2audio-selected-layer-codec-q2

Qwen2-Audio Selected-Layer Codec Compression (q2 + Zstd)

Method

Files

Important

Base model

Notes

alonsopg/
qwen2audio-selected-layer-codec-q2