Farzad Abdolhosseini
Farzad Abdolhosseini
No, I didn't have many clues to go on really.
Yes, if you disable `learn_augmentation`, you should also change both the loss to `cross_entropy` and `stats.checkpoint_metric` to `top1` (instead of `top1.logits`).
Original question: it seems to me like you’re running out of memory (RAM) and are getting OOM killed. I’d check the following a) RAM size (free) b) the dataset implementation...
Hi, I'm really confused about what the question is here. Please say: 1) what you did (e.g. a partial code containing what is registered) 2) what you expected 3) what...
It seems like the problem is that one of the submodules (i.e. the one that has the MuJoCo Cassie) is hosted on Gitlab. A quick way to fix it on...
Hmm, I haven't thought about this in a long time but you might be right. I did a quick check to see if this was handled in code (i.e. you...
Yeah I'll still need to spend more time on it, this is when I really hope I had better comments in the first place 😅 The short answer is that...
Hi there, I've taken a look before and I wasn't able to get any good performance (if at all) out of it, so currently for 70B inference we use VLLM...
@kadirnar this was simply a proof of concept. Unfortunately, combining vision into Ultravox is not part of our roadmap. What is your use-case?
The model in this PR will only be able to output text (not speech), but on the input side, yes it does allow for a combination of all three modalities:...