Steve

that solved it :( maybe a message stating that it should be launched as root would help others when you print: Error: Permission denied (os error 13)

I am having a similar issue while trying codellama through an openai compatible endpoint (litellm -> ollama). Would it be possible to support any model (so the list is not...

and similar issue with ollama/codellama -> ``` app-1 | Traceback (most recent call last): app-1 | File "/app/run.py", line 516, in app-1 | main(get_args()) app-1 | File "/app/run.py", line 512,...

the problem is not to implement litellm (it is an openai compatible endpoint), the problem is to be flexible in the name of the model in SWE-Agent. It would help...

for example, I wanted to experiment with codestral from mistral that "should" have good performance, and it is complex. What would be good is to provide or enforce the max...

I used the managed service offer (free for now) from https://xata.io/; my guess is that something was missing during the migration. happy to start again from a fresh start if...

I found the problem, the error message was misleading (the table exists); and I am not sure if the problem is on the xata side, prisma or somewhere else. pg_catalog.obj_description...

I confirm that the problem is still there; at least on the latest zfs on ubuntu: ``` zfs-2.1.5-1ubuntu6~22.04.4 zfs-kmod-2.1.5-1ubuntu6~22.04.1 ``` Pool was definitely created using linux/open-zfs