Hugging Face vs. Socialtext (discontinued)

If an organisation has more access to data and have access to high end computers like GPUs it’s recommended to use Hugging face as it will give better accuracy than any other models. If an organisation having less data and has less access to GPUsis looking for decent performance then traditional algorithms are more appropriate than hugging face

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.

• Model APIs
• Hugging Face Spaces for deploying demo apps
• Latest updated models available easily
• Vast support for language parsing and other relevant tasks

Incentivized

• Version history - Always keeps the edited versions and one can revert back any time
• Creating and Editing an article is very easy and intutive
• Sharing the articles with peers

• 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

There are some other services offer similar capacity as to Hugging Face, but not entirely the same. For example, amazon web services have a machine learning service called Comprehend, which offer a set of easy to use APIs to do machine translation and entity recognition and some other common NLP use case.

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.

• Hugging Face is cost and time saving.
• Pay is less, you pay what you use, doesn't affect much.
• Overall positive impact on business.

Incentivized

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