From f463268e362cafeabb7ec4568495514f7377ab56 Mon Sep 17 00:00:00 2001 From: "Chu,Youcheng" <70999398+cranechu0131@users.noreply.github.com> Date: Fri, 16 Aug 2024 14:29:06 +0800 Subject: [PATCH] fix: add run oneAPI instruction for the example of codeshell (#11828) * fix: delete ipex extension import in ppl wikitext evaluation * feat: add mixed_precision argument on ppl wikitext evaluation * fix: delete mix_precision command in perplex evaluation for wikitext * fix: remove fp16 mixed-presicion argument * fix: Add a space. * fix: add run oneAPI instruction for the example of codeshell * fix: textual adjustments * fix: Textual adjustment --------- Co-authored-by: Jinhe Tang --- python/llm/example/GPU/HuggingFace/LLM/codeshell/README.md | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/python/llm/example/GPU/HuggingFace/LLM/codeshell/README.md b/python/llm/example/GPU/HuggingFace/LLM/codeshell/README.md index e12e8163..e6117152 100644 --- a/python/llm/example/GPU/HuggingFace/LLM/codeshell/README.md +++ b/python/llm/example/GPU/HuggingFace/LLM/codeshell/README.md @@ -21,6 +21,12 @@ Suppose you have already configured GPU environment, you will need some extra pr ## 1. How to use this server +This is a required step on Linux for APT. Skip this step for PIP-installed oneAPI or if you are running on Windows. +```bash +source /opt/intel/oneapi/setvars.sh +``` + +Then run the following command in the terminal: ``` python server.py [--option value] ```