mshukor

Hello, I am testing the provided finetuned BASE text-to-image generation model and the quality of the generated images are very poor compared to those in the paper. I have similar...

Pile Dataset

1

Hello, Can you share your filtered Pile (180Gb) dataset? The paper mentions only truncation as preprocessing, can you provide more details about your filtering step? Also did you use specific...

BART Huge pretrained weights

1

Hello, We are interested in reproducing your work and it will be very helpful to have the pretrained BART Huge weights (used to initialize OFA Huge). Can you share the...

Helllo, I am trying to download Freesound following the provided example in [freesound.md](https://github.com/rom1504/audio2dataset/blob/main/dataset_example/freesound.md) , However, the example does not seem to work. Do you have any suggestions to fix that?...

Support multi-gpus training with accelerate

3

## What this does This PR supports training on multiple gpus using the `accelerate` librarie ## How it was tested Launching training on aloha sim with multiple GPUs and obtaining...

## Overview Support for PI0+FAST. Paper: https://arxiv.org/abs/2501.09747 Original JAX model: https://github.com/Physical-Intelligence/openpi * This is a working version that achieve around 50% success rate on LIBERO. This is with careful selection...