elven2016

Results 37 comments of elven2016

[BUG] Cannot read properties of undefined (reading 'error')

也遇到这个问题了，用了api方式，这个问题现在有找到问题原因了吗？

models suport for vicuna

vicuna-13b-v1.1 can loaded and work well! but the glm-10b model can not loaded, I have turn on the trust_remote_code ![image](https://user-images.githubusercontent.com/16677082/233778109-89c403ea-e30f-4590-90d9- 96fe217271e6.png)

发生错误：无法执行请求：获取“https://you.com/api/streamingSearch?q=%E4%BD%A0%E6%98%AF%E8%B0%81&page=1&count=10&safeSearch=Moderate&onShoppingPage=False&mkt=&responseFilter=WebPages%2CTranslations%2CTimeZone%2CComputation%2CRelatedSearches&domain=youchat&queryTraceId=6b01698c-8b27-44aa-994e-ff807feec13c&chat=%5B%5D“：拨打TCP 69.171.242.11：443：connectex：连接尝试失败，因为连接方在一段时间后未正确响应，或建立的连接失败，因为连接的主机无法响应。请确保您使用的是有效的 cloudflare 清除令牌和用户代理。

the same , how do you resolve it ?

Wireshark change causing error running osx via naked

the same issue too

Wireshark change causing error running osx via naked

> While attempting to setup Ventura for the first time using Docker-OSX, I came across this issue with not being able to generate a unique serial. The URL for `manuf`...

Centos 6.5 无法安装go

这个指导有问题，安装1.5执行会报错，下载1,4的然后安装就没有问题

A100 80 G fine tune llama-65b-hf got CUDAout of Memory

> What's your bitsandbytes version?你的bitsandbytes版本是什么？ Name: bitsandbytes Version: 0.38.1

A100 80 G fine tune llama-65b-hf got CUDAout of Memory

> > What's your bitsandbytes version?你的bitsandbytes版本是什么？ > > Name: bitsandbytes > > Version: 0.38.1 > > uninstall then try bitsandbytes==0.37.2 ？ I have use the default parameter to run fine...

A100 80 G fine tune llama-65b-hf got CUDAout of Memory

> > > What's your bitsandbytes version?你的bitsandbytes版本是什么？ > > > Name: bitsandbytes > > > Version: 0.38.1 > > > > > > uninstall then try bitsandbytes==0.37.2 ？ > >...

A100 80 G fine tune llama-65b-hf got CUDAout of Memory

> bitsandbytes==0.37.2 failed? Use 2 x 80G Only one card A100 80G