FergusFettes

The issue is the same as I posted here: https://github.com/hwchase17/langchain/issues/1368#issuecomment-1461853402 Chat models don't work for summarization in langchain, but there is no good reason for this. It is very easy...

If you are desperate to get this working, you can cherrypick the commit I made here: https://github.com/hwchase17/langchain/pull/1826 Then you can use turbo and gpt4 for chains etc.

Will the Chat model work as an LLM in agents and other places? Otherwise, I think it would be good to support 'gpt-3.5-turbo' as a regular LLM too. You just...

It looks like this issue can be closed. https://github.com/hwchase17/langchain/issues/1368#issuecomment-1465583175 for example is either using an old version of langchain, and old version of openai, or both. For anyone finding this...

For future reference, I got multi-token generating working with nnsight and implemented patchscopes here: https://github.com/jcoombes/obvs/pull/22

I'm also seeing this, and checked nvidia-smi in a seperate panel to confirm the GPU is being used. GPU column in scalene is empty.

I'm think I'm looking for the same thing: maybe this works for you? https://github.com/joerick/pyinstrument

I'm think I'm looking for the same thing: maybe this works for you? https://github.com/joerick/pyinstrument

`aws s3 ls s3://XXXX | head -n 1` does the same currently im buffering it via a tmp file `aws s3 ls s3://XXXX > /tmp/aws-log.txt && cat /tmp/aws-log.txt | head...

This demo is good but one thing that took me a while was figuring out how to take advantage of typers nice help printing: ```python from typer import Context, Typer...