Apoorv Khandelwal

Thanks @krrish94! That would be good and I will let you know if I find any solutions in the near term.

I have transferred this issue to allenai/allenact, because the robothor-objectnav branch in allenai/embodied-clip (that you are training from) is exactly equivalent to allenact v0.5.0.

Hey there, I needed Notebooks and Quick Sheets support, so I modified remarks to handle these. I made many changes at once, but the idea is simple (if no PDF...

This is great, thanks lucasrla! Glad you were able to take a look and get it implemented. (I'm traveling, so a PR would have taken me much longer to get...

I am having the same issue -- using resnet50, `visual_encoder.output_shape` is currently set to `(42, 7, 7)` (as it should be). But actually, the model produces features of size `(42,...

Something like `pip install 'remarks @ git+https://github.com/lucasrla/remarks'` (with python 3.10) might work for you!

Have you made any progress on this? Looking to train AttnGAN with multiple GPUs in the very near future.

Hey, it's great to see that mamba is being integrated in Transformers! Just wondering, is there a timeline or ETA for this PR? Thanks so much.

Any thoughts about this? Maybe also cc @stas00?

Very cool, thanks a ton! I will try it out and let you know.