Hugging Face vs. Socialtext (discontinued)

Hugging Face is an excellent starting point when working on NLP projects; it is also great for prototyping and developing pipelines for NLP tasks, being those tasks general like embedding representation or specific, like SQUAD models and datasets. It needs more phonetic models or datasets to be as advantageous in that regard.

Incentivized

We use Social Text as a platform to air our issues with different departments. We voice our concerns and suggestions so we can help find a solution to the problems we incur on a daily basis. We need to have social text as an app so we can communicate in real time not only during work hours.

• Has access to hundreds of models useful for any NLP usecase.
• Gives better accuracy on prediction tasks.
• Easy to test the model in the website itself to check the accuracy without actually implementing it.
• Has many algorithms for all the prediction problems.

Incentivized

• Ease of the use of application
• Application does not freeze while attaching data files or pictures
• Unlimited data storage

• Most of the Hugging face models are of big size, hence difficult to work if there is no access to high computational system like GPU.
• It’s good to have some visualization tool in hugging face for viewing model architecture.
• I recommend to implement hugging face lite version so that it can run on any system with less specifications.

Incentivized

• Search needs a ton of improvements. It was very slow a year ago
• Search result quality was also not that good
• I know they have improved their UI recently but when i used it last year it did not really have any design elements which could be used to make the articles look more presentable. It was important for us as we used it for external communication as well.

We have a lot of info in Socialtext already. It would be hard to get all that info out and port it to a different system

Hugging face is the latest technology built using transformers hence it gives better performance than other similar products.

Incentivized

I frankly like Confluence better than socialtext because of the speed and the quality of search. They also have better design elements which can help make the articles pleasant to the eyes.

• Reduced the time spent drastically in building complex transformer models
• Very quick deployment of demo apps, that reduces the time spent on making UIs

Incentivized

• We get solutions to concerns much faster
• We promote interactions with the other depts
• We listen and have discussions