omer

Results 5 issues of omer

1. 在Ubuntu 20.4的Docker容器上编译安装 2. GCC 9和GCC 11版本都试过了,一样的报错 3. 机器是老的Dell R720,可能CPU比较老 麻烦帮忙看下 ``` In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:47, from /root/app/fastllm/include/utils/utils.h:21, from /root/app/fastllm/src/fastllm.cpp:5: /usr/lib/gcc/x86_64-linux-gnu/11/include/avx2intrin.h: In member function 'void fastllm::Data::CalcWeightSum()': /usr/lib/gcc/x86_64-linux-gnu/11/include/avx2intrin.h:119:1: error: inlining...

使用chatglm-6b-int8.flm在24G的GPU上运行,理论上内存是足够用的。 但是运行一段时间后会异常,控制台报错: terminate called after throwing an instance of 'char const*' python会进入状态,挂住。 请问: 1. 是否有其他的详细日志供排查分析? 2. 进入这个状态后,是否有办法自动重启?

有一些项目环境没有GPU,想请问下如果用CPU跑XLNet,有推荐的加速框架么?

stale

User can config the `Model Name` in Settings to test GPT4-o or other new models like below: ![image](https://github.com/sparrow-js/an-codeAI/assets/11539396/09a183d7-7b81-44c3-9d0f-e7ac20cd79c0) and the default value keep the same as before. for #90

To accommodate new models, allow users to set `ModelName` themselves.