凤
weixin_44093752/mbasimplifier
Model Introduction
Files & versions
Pull Requests
Discussion
Analysis

MBA Simplifier Ascend NPU smoke adaptation

This delivery tracks the official qox/mba-simplifier snapshot:

  • https://huggingface.co/qox/mba-simplifier

The model card describes a three-layer MBA simplification pipeline with an optional neural-guided rule classifier. The live revision was checked on 2026-08-23: 4671ebd370b8c4dfaa10b05515ce053a8960c946.

The neural mba_classifier.safetensors is 8,903,168 bytes with SHA-256 cb8c272eca983366cda13b1681a64afb23f049fcafebf2f0fb26cd85c67fae4e.

Run

Download the files listed in model-lock.json into /tmp/model-agent/mbas, then run:

python inference.py --model-path /tmp/model-agent/mbas --device npu --output validation/runtime.json

The script reconstructs the official rule-classifier Transformer, strictly loads the checkpoint, tokenizes one bounded MBA expression, and runs one forward on npu:0. On the verified Ascend910, strict loading succeeded for 2,224,474 parameters, output [1,90] was finite, and the forward took about 0.202241 seconds. CANN reported that aten::_transformer_encoder_layer_fwd fell back to CPU; this is recorded as a runtime compatibility boundary. No full simplification accuracy gate is claimed.

Evidence

Model Agent CPU/NPU 推理工作流

Ascend NPU 设备调用

CPU/NPU 精度验证结果