This private repository contains the final PEFT LoRA adapter for PTXBench Qwen3.6-27B-s1. It was trained from Qwen/Qwen3.6-27B with rank 32 on the s1 configuration of Genghan/PTXBench-Qwen3.6-27B-SFT.

Qwen3.6 represents each linear-attention Q/K/V input projection as one fused in_proj_qkv module in Transformers. The release adapter therefore rewrites each independently trained rank-32 Q/K/V triplet as one mathematically equivalent block-diagonal rank-96 adapter. All other modules remain rank 32. See FUSION_PROVENANCE.json for the conversion details.

Run python merge_adapter.py to create a standalone merged model directory. The merge requires the full base-model download and substantial CPU memory and disk space; it does not require a GPU.

This checkpoint is intended for research on CUDA kernel generation and repair. It inherits the limitations of the base model and may emit incorrect or unsafe CUDA. Generated kernels must be compiled and evaluated in an isolated environment before use.