ipex-llm
ipex-llm copied to clipboard
Add CPU and GPU examples for DeciLM-7B
Description
In this PR, we add CPU and GPU examples of DeciLM-7B using bigdl-llm's transformer and optimize_model API. This is the issue page: https://github.com/analytics-zoo/nano/issues/936
Please also updated the readme for Windows GPU supports as we have done here: https://github.com/intel-analytics/BigDL/pull/9992
It would be better to have some verification on Windows GPU.
Please also updated the readme for Windows GPU supports as we have done here: #9992
It would be better to have some verification on Windows GPU.
Sure, I'll do it.
I've updated README file and finished verifications on windows GPU.
It can work when I set cpu_embedding=True for both HF-transformer API and Pytorch API.