Modelpublic

MilyaShams/Qwen3-1.7B-PTQ_W8A8

sourceHugging Faceupdated 6mo agoView on Hugging Face

0likes33downloads

Model Card

Compressed Model: MilyaShams/Qwen3-1.7B-PTQ_W8A8

This model was compressed using the llmcompressor framework.

Compression Details

—Base Model: Qwen/Qwen3-1.7B
—Experiment Name: PTQ_W8A8
—Recipe / Modifiers Applied:

python

config_groups=None targets=['Linear'] ignore=[] scheme='W8A8' kv_cache_scheme=None weight_observer=None input_observer=None output_observer=None observer=None bypass_divisibility_checks=False index=None group=None start=None end=None update=None initialized_=True finalized_=None started_=True ended_=True

Note: This model card was automatically generated. All structural modifiers and parameters used during compression are logged above.