Milad Aghajohari

CUDA out of memory

2

Hi! Thanks for the great repository. I am using your approach to do link prediction on a dataset and this dataset has a lot of nodes, it has near 60000...

fix the docs for gru cell

3

Here it is written the LSTM cell which is clearly a GRU cell. It can be misleading. # What does this PR do? Fixes # (issue) ## Checklist - [...

converting docker images to singularity

6

### Feature request I am trying to run tgi in a HPC cluster. I tried pulling the docker images with singularity. The problem is that in that case the custom...

Hi! Thanks for the great tool! Would you mind adding residual connections to it?

can I work on making a flax attention function out of this repository?

1

Hi lucidrain! I wanted to use flash attention in one of my projects. I wanted a transformer model that works on sequences as long as 2400 with a batch size...

save_state removes shared weights but load_state cannot load properly

4

### System Info ```Shell accelerate version: 0.27.2 python: 3.11 ``` ### Information - [ ] The official example scripts - [X] My own modified scripts ### Tasks - [ ]...

OpenAI models does not support multi modal?

3

I tried the multimodal code example with gpt-40 and the output has no relation to the provided image while the code does not raise any error.

RPS is not deterministic and not seeded correctly.

1

### Describe the bug I am just running the rock paper scissor example of pettingzoo [here](https://pettingzoo.farama.org/content/environment_creation/). I found out if I run the code multiple times, I get different plays....