Saumya Gandhi
Saumya Gandhi
Hey @imabp and @ksdkamesh99 , can I work on the greetings bot?
I think this has become more important now. I was trying to use base model as `gpt-4-turbo-preview` but was getting litellm errors saying model could not be mapped correctly. I...
Right, that makes sense! In prompt2model_demo.py and .ipynb, user manually selects the dataset number/name. maybe it makes sense to inform the user that the dataset is gated and they should...
yeah I think a fall back mechanism makes sense
just ran into the same issue myself. I think that makes sense @lewtun . I should be able to make a PR for this over the weekend. Just putting this...
coming very soon!
Hey Orlando! We have a helper for doing Async RL. check out `art.trajectory_group_batches()`. example of using it can be found in https://github.com/OpenPipe/ART/blob/aab795fe3fcede8b69744e7b1e43f6fe5f4961f9/dev/tau-bench/run_rl.py#L247 . However, we have seen some stability issues...