Tanishq Abraham

Resources mentioned in the book

4

As I discussed with @jph00 on Discord, there are several resources mentioned in the book that are supposed to be added to the book website (originally mentioned to be https://book.fast.ai...

FastCUT LR schedule.

2

I was looking through the default options, and I noticed that for FastCUT, the default learning rate schedule was 150 epochs at constant LR and 50 epochs decaying the LR...

Feature request: Specifying GPU IDs

1

It would be ideal to specify the GPU IDs that a script can use. i typically like to have a GPU ID argument in my script so that I can...

multi-GPU support

2

I need to check if fastai's [multi-GPU support](https://docs.fast.ai/distributed) work with my package, and if not, what needs to be modified to get it to work. Additionally, I may need to...

[This](http://upit-cyclegan.herokuapp.com/) Gradio demo should be transferred to HuggingFace Spaces now, now that it is the main place to freely host ML demos.

Add metrics and test model tracking callbacks

5

I want to add support for metrics, and even potentially include some common metrics, like FID, mi-FID, KID, and segmentation metrics (for paired) etc. Additionally, monitoring the losses and metrics,...

Here are some tests of interest: - [ ] Test the loss (example fake and real images for the reconstruction loss and discriminator) - [ ] Check the batch independence...

MultiMedQA

3

This PR implements the [MultiMedQA](https://arxiv.org/abs/2212.13138) suite of tasks: 1. Adds MedQA 4-options task 2. Added MedMCQA task 3. Adds MultiMedQA group that includes the above-mentioned tasks and also PubMedQA and...

run_lora_clm.py support for other datasets

2

### Feature request right now [the script](https://github.com/huggingface/optimum-habana/blob/main/examples/language-modeling/run_lora_clm.py) is hardcoded for either `"tatsu-lab/alpaca"` or `"timdettmers/openassistant-guanaco"` and using any other dataset throws an error. ### Motivation It would be nice to be...