What you can do with Hugging Face
Every task in plain language. Pick one, and we can help you get access.
81 things you can do
Hugging Face
The AI community building the future with open-source machine learning models, datasets, and applications.
14 multi-step recipesRecipes: multi-step jobs
Chat Completion with Model DiscoveryConfirm a router model is available and run a chat completion against it.Create Repository and Configure
Create a Hub repository and apply visibility and gating settings.Dataset Filter Rows
Apply a SQL-like filter to a dataset split after confirming filter support.Dataset Search and Statistics
Search a dataset split and pull descriptive statistics for the same split.Dataset Size and Parquet Files
Verify a dataset, read its size profile, and list its Parquet files.Dataset Validate and Preview
Validate a dataset, discover its first split, and preview its first rows.Deploy Inference Endpoint and Wait
Create a dedicated Inference Endpoint and wait until it is running.Discover a Space
Find a Space by search term and load its detailed record.Embeddings Pair
Embed a query and a document with the same model for similarity comparison.Grounded Text Generation
Discover a text-generation model on the Hub and generate text with it.Search and Inspect a Model
Find a model by search term and inspect it at a chosen revision.Summarize Then Translate
Summarize a document and translate the resulting summary.TGI Inspect and Generate
Inspect a TGI server, tokenize a prompt, and generate text from it.Toggle Inference Endpoint State
Pause a running endpoint or resume a paused one based on its current state.
Artificial Intelligence Management
Deploy a new Inference EndpointChange an endpoint's model, hardware or scalingPermanently delete an Inference EndpointPause an endpoint to stop compute costsResume a paused endpointScale an endpoint down to zero replicasGenerate an image with a chosen Hub modelComplete a prompt via the completions APIGenerate text in one response on TGIStream generated tokens over SSECreate text embedding vectorsRun inference on any Hub modelRun inference by task with a recommended modelContinue a prompt with a language modelClassify text, such as sentimentExtract an answer from a context passageSummarize a long textTranslate text between languagesFill a masked word in a sentenceExtract embeddings with a chosen Hub modelClassify text into labels you supplyScore similarity between sentencesGenerate images from a text promptList Inference Endpoints in a namespaceGet an Inference Endpoint's detailsRead an endpoint's runtime logsGet an endpoint's traffic and latency metricsSearch models on the HubGet Hub details for one model repoGet a model's info at a specific revisionList model tags grouped by typeGet an inference provider model's infoModel Inference
Get a chat completion via the inference routerSpeech & Voice
Transcribe audio with a specific Hub modelTranscribe an uploaded audio fileTurn text into spoken audioOther things you can do
Create a model, dataset or Space repoDelete a repository from the HubChange a repo's visibility or gatingPreview the first rows of a dataset splitPage through rows of a dataset splitList Parquet files via the Dataset ViewerGet a dataset's row count and byte sizeGet column statistics for a dataset splitGet a dataset's Croissant metadataCheck if a dataset works in the Dataset ViewerList a dataset's subsets and splitsSearch datasets on the HubGet details about one datasetList a dataset's auto-converted Parquet filesList dataset tags grouped by typeIdentify the authenticated Hub userList cloud providers and regions for endpointsFull-text search rows in a dataset splitFilter split rows with a WHERE clauseShow the model loaded on a TGI serverGet TGI server version and model metadataCheck whether a TGI server is readyScrape TGI Prometheus metricsTokenize text with the loaded model's tokenizerSearch Spaces on the HubGet details about one SpaceShowing 64 of 67. Search above to find the rest.