Krish Dholakia

Answer Extraction

4

Hi @patil-suraj , Using the E2E QG model, curious how I can extract the answer span the question was generated for, in this model ?

Generate exact number of questions

6

Hi, Great work on the library 🎉, it's super useful. Is it possible to generate a specific number of questions ? I know we have 'num_return_sequences' but i've seen that...

Continuous Question Generation

4

Hi @patil-suraj , Would it be possible to generate new questions for a given document, given previous questions/answers for the same ? I've read some papers in the area but...

Deploy model

6

Hi, I'm trying to deploy this model via torch serve. But when i try and save the tokenizer: `tokenizer = AutoTokenizer.from_pretrained("valhalla/t5-base-e2e-qg") tokenizer.save_pretrained('/dummy_location') ` it does not save a vocab.txt, instead...

Speed of model

1

Hi, I was wondering if it was possible to do some fine-tuning to make the model run faster ?

Image inpainting

4

Hi, 2 quick questions around this: - Is there any colab / guiding doc around leveraging this model for image inpainting? - Given a source person + t-shirt image, how...

Bitmoji's as the source image ?

1

Hey, i'm really interested in using this on bitmojis. But none of the checkpoints seem to be generating satisfactory results. Any advice for the best way to leverage human driving...

Setting component to rerender when script loaded

2

Currently I have a component: QuickAdd that needs the google autocomplete api to run However, while the component renders, it doesn't seem like the autocomplete has finished loading. If i...

### Describe the bug When I upload an image on my iphone it gets rotated vs. uploading the same image on desktop. I assume this might have something to do...

inpainting doesn't work with CPU

5

### Describe the bug Using the inpainting example but trying to run it on the cpu instead of gpu (since i'm trying to push to hf space). Hitting this runtime...