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

Vietnamese Address Normalizer Ascend NPU smoke adaptation

This delivery tracks the live qox/vn-address-normalizer checkpoint. The model card describes a 26M-parameter character-level Transformer for Vietnamese address normalization:

  • https://huggingface.co/qox/vn-address-normalizer

The Hugging Face revision was checked live on 2026-08-23: 5d0de6d07356774e861f72684e4807bdbc137351. The public snapshot provides model.safetensors at the repository root (26,368,100 bytes) with SHA-256 4fcaae4f7a2e725aad234533e579884daa227c761b82c1c6a82c7ff73bbc2e3a.

The upstream inference.py currently expects additional vocabulary files and a nested weight path that are not present in the live snapshot. This delivery therefore includes a self-contained inference.py with the same official S2S architecture and strict checkpoint loading, so the execution gate is reproducible without claiming address-normalization accuracy.

Run

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

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

The script uses bounded deterministic token tensors, executes the official encoder/decoder architecture on npu:0, and fails when an explicitly requested Ascend device is unavailable. On the verified Ascend910, strict loading succeeded for 6,589,197 parameters, output [1,269] was finite, and the forward took about 0.124086 seconds. CANN reported that aten::_transformer_encoder_layer_fwd fell back to CPU; this is recorded as a runtime compatibility boundary, not as a full NPU-kernel precision claim.

Evidence

Model Agent CPU/NPU 推理工作流

Ascend NPU 设备调用

CPU/NPU 精度验证结果