onnxruntime-node
2023/12/3 0:16:00
node_modules/onnxruntime-node/bin/napi-v3/linux/x64/libonnxruntime_providers_cuda.so
2024/12/21 15:49:00
694.3 MBあってデカい
onnxruntime-nodeでgzipで圧縮したonnxファイルを読み込む
2023/12/3 0:17:00
const onnx_zip = fs.readFileSync('./sonoisa_sentence-bert-base-ja-mean-tokens-v2_onnx/model_quantized.gz');
const onnx_buffer = zlib.unzipSync(onnx_zip)
const session = await ort.InferenceSession.create(onnx_buffer);