CoolFace
Modelpublic

EmbeddedLLM/Phi-3-mini-128k-instruct-onnx-cpu-int4-rtn-block-32-acc-level-4

sourceHugging Facemitupdated 2y agoView on Hugging Face
0likes9downloads
Model Card

EmbeddedLLM/Phi-3-mini-128k-instruct-onnx-cpu-int4-rtn-block-32-acc-level-4

Performance Metrics

<!-- These are the evaluation metrics being used, ideally with a description of why. -->

CPU-INT4-RTN-BLOCK-32-ACC-LEVEL-4

We measured the performance of CPU-INT4-RTN-BLOCK-32-ACC-LEVEL-4 on AMD Ryzen 9 7940HS /w Radeon 78

Prompt LengthGeneration LengthAverage Throughput (tps)
128128-
128256-
128512-
1281024-
256128-
256256-
256512-
2561024-
512128-
512256-
512512-
5121024-
1024128-
1024256-
1024512-
10241024-