hjLabs AI Playground
Starting the on-device runtime…
distilbert-base-uncased-finetuned-sst-2-english is the workhorse sentiment classifier — 67 MB, and it returns a positive/negative label with a confidence score in a few milliseconds once loaded. Useful for triaging reviews, support tickets or survey free-text without shipping customer comments to a third-party API. A toxicity model (toxic-bert) is available on the same page when you need to flag abusive content rather than polarity.
sentiment analysis onlinefree sentiment analysis tooldistilbert sst-2text classification browserreview sentiment checkertoxicity detection onlineno api sentiment analysis
Poorly, like every binary classifier. SST-2 was trained on movie reviews, so it is confident and often wrong on sarcasm, negation-heavy sentences and text that is positive about one thing and negative about another. Treat the score as a signal, not a verdict.
No. The model weights are downloaded from Hugging Face to your browser once, and every inference after that runs on your own GPU through WebGPU. Your text, images and audio are never sent anywhere — hjLabs.in has no inference server and no way to see your input.
Small models do. Recent mobile Chrome and Safari expose WebGPU, but memory is the binding limit — stay under roughly 200 MB of weights on Android, and expect iOS to reclaim the tab sooner. The catalog shows every download size up front so you can pick something that fits.
That depends on the individual model, not on this site. Each model page links to its Hugging Face repository, where the licence is stated — most of the catalog is Apache-2.0 or MIT, a few are research-only. We add nothing on top: hjLabs.in claims no rights over anything you produce here.