course-nlp VS huggingface_hub

fast.ai also has an NLP course.

fastai already has a course that covers traditional nlp as well

My question: How do you think high-quality online resources such as https://missing.csail.mit.edu/, https://fullstackopen.com/en/, http://allendowney.github.io/ThinkBayes2/, https://www.fast.ai/2019/07/08/fastai-nlp/ compare to the online education from OMSCS? Do any of my reasons above ring false for you?

8 - Code-First Introduction to Natural Language Processing - fast.ai

fast.ai are doing the best work democratizing AI (machine learning and neural networks), including natural language

Can't recommend the course enough and it's incredible that such a quality resource is available for essentially zero cost

https://github.com/fastai/course-nlp

https://www.youtube.com/playlist?list=PLtmWHNX-gukKocXQOkQju...

fastai nlp course

[1] Chapter on LSI from Introduction to Information Retrieval [2] A Code-First Approach to Natural Language Processing by fast.ai [3] Computational Linear Algebra by fast.ai [4] https://www.cc.gatech.edu/~hpark/papers/nmf_book_chapter.pdf

NLP

Something to think about:

https://github.com/huggingface/huggingface_hub

Yes! We have a well documented Python library (https://github.com/huggingface/huggingface_hub) and public endpoints (https://huggingface.co/docs/hub/api#endpoints-table) you can use to retrieve information about the models and potentially build UIs with specific use cases in mind

i think if you search for pixel art here there are some models worth checking out: https://huggingface.co/

I received another error saying OSError: We couldn't connect to 'https://huggingface.co' to load this model, couldn't find it in the cached files and it looks like ./vae is not the path to a directory containing a file named diffusion_pytorch_model.bin

I plan to release it on https://huggingface.co/, where all this cool AI stuff is available for free for everyone that wishes to try it.

For this I used mainly the chainner application with models from here but I also used the google colab automatic1111 stable diffusion webui (for example for Lanczos) and also spaces fromhuggingface like this one or then from the replicate.com website super resolution collection.

you will now need to create a huggingface account ( https://huggingface.co/) if you haven't already. When you have, go here and accept the terms, https://huggingface.co/runwayml/stable-diffusion-v1-5. When you have done both, click on your profile icon and go to settings. Click access tokens and then create token, name it whatever you want, select "write". When you are finished with all this, then you can run the next cell which is the hugging face cell. It will ask for a token, you copy and paste what you just created.