-
Unrecognized and not translated. how to fix it?
![2022-12-30_12-01-59](https://user-images.githubusercontent.com/49092250/210053046-bb833d43-dd88-4afc-b655-dcbb49d8a37b.png)
![bboxes](https://user-i…
-
That model is insane for its size ....
https://huggingface.co/microsoft/Phi-3-vision-128k-instruct
-
## Motivation
The [Hugging Face](https://huggingface.co/) Hub provides a platform hosting a collection of pre-trained models, datasets, and demos of machine learning projects. This [blog](https://…
-
Some times, we have to be capable of detecting and recogniting two layers car license plate.This method does a good job on single layer car plate?But when it comes to two layer, it does badly.So are t…
-
### Question
Hi, i create a llava model with only 12 layers (instead of 32 layers). However, the evaluation on TextVQA two times slower than the larger llava 7 billion parameters
Code to create …
-
While working on a mapping of bibliographic language codes (ISO 639-2/B due to the RDA application guidelines of the German National Library https://wiki.dnb.de/download/attachments/127172808/Kapitel_…
-
I downloaded the get_cocotext_recognizer_dataset using the example you showed and I thought that a large dataset like this would help in good training. But the loss is very high. What parameter can I …
-
### What features would you like to see added?
It would be great if we could upload PDFs or text documents and have it processed as input context versus the current workflow which uses the RAG API …
-
I was wondering whether the provided images underwent some kind of preprocessing (denoising / normalization). Then I stumbled over this step in the training script:
https://github.com/ulb-sachsen-a…
-
For Kuroinu 2 redux. There is no hook code available by default. I tries manually searching for text and it seems to work for only a couple lines.