Bryce Meyer
Bryce Meyer
Can you share some of your generations as an example on this issue? I have a list of models that need to be investigated, and generally the meta-llama family hasn't...
Very interesting. Finally, if you can share the code you are using in vllm to generate this text, that will be very useful to expedite recreating this issue.
There is a low priority task to separate the HookedRootModule into it's own file, which could then be used as described, as well as making it easier for people to...
The PR that was originally created for this issue can be picked up again, and we can probably wrap up where @andyrdt was.
@cmtkapchorowa What do you mean by a virtual machine? Like within parallels, or something?
Thank you for bringing this up. We can probably work this into the next major release of TransformerLens.
Hey all, I am making this my second priority at the moment. One thing to note is that multi-gpu support hasn't really been made very clear in the project. I...
Hey @ArthurConmy, do you want me to take over on this? Looks like we will be able to wrap up 2.0 tomorrow, and I would love to get moving on...
There are quite a few differences compared to the current released version of TransformerLens. I would be curious to see this test running against that current version. In the current...
3.0 is coming sooner rather than later. We can definitely work this into that release.