Qwen2-Audio Selected-Layer Codec Compression (q3 + Zstd)

This repository contains a custom compressed artifact derived from Qwen/Qwen2-Audio-7B-Instruct.

Method

Selected-layer codec compression over MLP/feed-forward style linear layers:

mlp
feed_forward
up_proj
down_proj
gate_proj

Compression setting:

Quantization: q3
Compression: Zstd

Files

compressed_model.pt
compression_metadata.json

Important

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

Base model

Qwen/Qwen2-Audio-7B-Instruct

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support