TomExMachina

Results 12 comments of TomExMachina

> Hi @barthfab @LuciferianInk, > > We extended the context length to 8192 for the latest models that use multi-query attention (Llama 2, StableBeluga 2, CodeLlama, etc.). Feel free to...

No commts or PR were linked here or I might attempt a new PR myself.

Just realized this has happened to me. This is a nightmare on Arch if you already deleted the pre-upgrade snapshot. Now seeking temporary virtualbox or vmware alternatives which I have...

Don't we have all the training data to just do that on our own? The fine-tuning shouldn't be that hard to get training.

ugh maybe not https://github.com/ShishirPatil/gorilla/issues/46 . I haven't read a self-instruct paper. Isn't it just doing inference to generate more training data? Maybe jsonformer is involved. idk edit: Okay so no...

> self-instruct code is definitely not open sourced yet. You can send me email and we can discuss some details if you are interested in. @cquliujian @FanWan This using AST...

It will probably be a good idea to spend a considerable amount of time and effort figuring out whether or not this integration is even a good idea. At the...

Should be fixed by https://github.com/jaemil/agentsflow/commit/0889bdcf823c51ee91dbc54bfde8c6192539f8fc which was confirmed on Linux and Windows and merged to main. @bonadio please start over, and follow new instructions in README.md

It was mentioned (I think in the FAQ) that this would not be done. Not a bad idea for a fork though.

Also, maybe we could define what a version 0.1.0 or even 1.0.0 is supposed to look like (And maybe that's Big Sexy)