Brandon Biggs

I'm also interested in using other LLMs. I haven't tested it yet, but it looks like we may be able to just change the URL specified here - https://github.com/whoiskatrin/chart-gpt/blob/afb3c7b8322f92941933a7cba2f5bca02121a738/pages/api/get-json.ts#L22 as...

I had a similar issue when calling the API from Windows due to how Windows can encode some characters.

I run a few models on multiple GPUs. Here's my bash script to launch an API: ```bash export CUDA_VISIBLE_DEVICES=0,1 python3 -m fastchat.serve.model_worker \ --num-gpus 2 \ --model-path /path/to/model \ --host...

I've been exploring this as well. My local files are in `~/.cache/galactica/`. The comment in the code seems to be off. It indicates `~/.cache/galai/` but the code shows `~/.cache/galactica/` -...

This is usually solved by running `pip install transformers`.

I was looking for something similar and stumbled upon this page. Maybe this will help someone else in the future - https://www.linuxwave.info/2022/04/running-postgresql-database-using.html

Looks like it's a permissions issue `Operation not permitted `. Can you provide additional details on how you're trying to create/run the docker container?

I went through other issues and pull requests and found that someone had fixed it and submitted a PR - https://github.com/LLNL/msr-safe/pull/158. Testing with these changes seems to fix the issue.

> _Note_: when compiling MPI programs, however, one tends to use wrappers (`mpicc`, `mpif90`, `mpif08` ...) which automatically handle the MPI set up behind the scenes (include paths, library paths...

> The `hints` section is not language-specific indeed. Given that compilation is not specific to an exercise, since the same compilation / execution command pair can be used throughout all...