lux
lux
add 1*10^-16 on every pixel may help
i have compiled a working version as a temporarily fix and uploaded to my fork, feel free to check it out [https://github.com/luixiao0/ollama/releases](url)
check #393 , openBMB's work is merging to master, you may need to compile ollama from source
> 直接用主分支？我试试 please check the latest comment in #393 , start from master and merge openBMB's fork is needed, you can also use my precompile and docker image temporarily update:...
related #393
same issue here
testing locally
i am not a professional cpp programmer, the following discoveries may not correct, i cherry-picked cpm-v2.6 code to 2.5 branch(quatntized gguf from hf) and makes embedding working 1. maintainers of...
> 抱歉，我刚开始可能没看清楚。我会尽快在check下ollama这个分支，我开始以为只是llamacpp会跳出的问题。 这几天刚开源，对我们团队来说，一下子问题有点多，我们会尽快解决。 No worry, excellent work, python inference works outof the box anyway 😆
successful run on ollama with latest commit, great work