Modelpublic

dopaemon/Gemma4-E4B-8B-Heretic-Ultra-QLora-Reverse-Engineering

sourceHugging Faceupdated 18d agoView on Hugging Face

1likes

Model Card

Gemma4 E4B 8B Heretic Ultra — RE QLoRA adapter

QLoRA adapter trained with mlx-lm on top of dopaemon/Gemma4-E4B-8B-Heretic-Ultra-MLX-4Bit, for the task of recovering the original function name from stripped, decompiled C-like code.

—~2000 rows of decompiled function/name pairs at -O0 (unoptimized x86), then
—~2000 rows at -O2 (optimized x86, more inlining), resumed from the -O0 adapter.

bash

mlx_lm.generate \
  --model dopaemon/Gemma4-E4B-8B-Heretic-Ultra-MLX-4Bit \
  --adapter-path <this repo> \
  --prompt "..."

or with mlx_lm.server --adapter-path <this repo>.