Hugging Face Hub - Discover Models, Datasets & Spaces from 500K+ AI Resources

Search and explore the world's largest AI resource repository. Find models by task, discover datasets for training, explore ML demo spaces, and track trending AI resources. Perfect for ML research, model selection, and staying current with AI developments. No API token required for basic searches.

Features

• Search Models - Find ML models by name, task, or framework
• Search Datasets - Discover training and evaluation datasets
• Search Spaces - Explore ML demo applications
• Get Model Details - Retrieve comprehensive model information
• Get Dataset Details - Full dataset metadata and file lists
• List Model Files - Browse repository file structure
• Get Model Cards - Read documentation and usage info
• Trending Models - See what's popular now
• Trending Datasets - Track hot datasets
• Filter by Task - text-generation, image-classification, etc.
• Filter by Framework - transformers, diffusers, pytorch, etc.
• Demo Mode - Test with sample data before going live

Who Should Use This Actor?

ML Engineers

Find the best models for your use case. Compare options. Discover new architectures.

Data Scientists

Search datasets for training. Find evaluation benchmarks. Explore data sources.

AI Researchers

Track trending models. Monitor field developments. Find papers and implementations.

Product Managers

Evaluate AI capabilities. Research model options. Understand ML landscape.

Developers

Find models to integrate. Check model requirements. Get implementation examples.

AI Enthusiasts

Explore cutting-edge ML. Try demo spaces. Learn about new models.

Quick Start

Demo Mode (Free Test)

{
  "task": "search_models",
  "query": "text generation",
  "demoMode": true
}

Search Models

{
  "task": "search_models",
  "query": "sentiment analysis",
  "taskType": "text-classification",
  "library": "transformers",
  "limit": 20,
  "demoMode": false
}

Search by Task Type

{
  "task": "search_models",
  "taskType": "text-to-image",
  "sort": "downloads",
  "direction": "desc",
  "limit": 10,
  "demoMode": false
}

Get Model Details

{
  "task": "get_model",
  "repoId": "meta-llama/Llama-2-7b-hf",
  "demoMode": false
}

Search Datasets

{
  "task": "search_datasets",
  "query": "instruction following",
  "limit": 20,
  "demoMode": false
}

Get Dataset Details

{
  "task": "get_dataset",
  "repoId": "tatsu-lab/alpaca",
  "demoMode": false
}

Search Spaces (Demos)

{
  "task": "search_spaces",
  "query": "stable diffusion",
  "limit": 10,
  "demoMode": false
}

Get Space Details

{
  "task": "get_space",
  "repoId": "stabilityai/stable-diffusion",
  "demoMode": false
}

List Model Files

{
  "task": "list_model_files",
  "repoId": "meta-llama/Llama-2-7b-hf",
  "demoMode": false
}

Get Model Card

{
  "task": "get_model_card",
  "repoId": "mistralai/Mistral-7B-Instruct-v0.1",
  "demoMode": false
}

Trending Models

{
  "task": "trending_models",
  "limit": 20,
  "demoMode": false
}

Trending Datasets

{
  "task": "trending_datasets",
  "limit": 20,
  "demoMode": false
}

Input Parameters

Parameter	Type	Default	Description
task	string	required	Task to perform (see task list)
apiToken	string	-	HF token (optional, for private repos)
query	string	-	Search query
repoId	string	-	Repository ID (org/model-name)
taskType	string	-	Filter by ML task (pipeline_tag)
library	string	-	Filter by framework
filter	string	-	Additional filter criteria
sort	string	-	Sort field (downloads, likes, trending)
direction	string	"desc"	Sort direction (asc, desc)
limit	number	20	Max results to return
includeCardData	boolean	false	Include full card data
webhookUrl	string	-	Webhook URL for results
demoMode	boolean	true	Return sample data

Available Tasks

Task	Description
search_models	Search for ML models
get_model	Get model details
search_datasets	Search for datasets
get_dataset	Get dataset details
search_spaces	Search for ML demos
get_space	Get space details
list_model_files	List files in model repo
get_model_card	Get model documentation
trending_models	Get trending models
trending_datasets	Get trending datasets

Common Task Types (pipeline_tag)

Task Type	Description
text-generation	LLMs, chatbots
text-classification	Sentiment, spam detection
translation	Language translation
summarization	Text summarization
question-answering	Q&A from context
text-to-image	Image generation
image-classification	Image categorization
object-detection	Object detection
automatic-speech-recognition	Speech-to-text
text-to-speech	Speech synthesis

Common Libraries

Library	Description
transformers	Hugging Face Transformers
diffusers	Diffusion models (SD, etc.)
pytorch	PyTorch models
tensorflow	TensorFlow models
sentence-transformers	Embeddings
spacy	spaCy models

Output Format

Search Models

{
  "success": true,
  "query": "sentiment analysis",
  "models": [
    {
      "id": "distilbert-base-uncased-finetuned-sst-2-english",
      "author": "distilbert",
      "downloads": 5420000,
      "likes": 892,
      "tags": ["text-classification", "pytorch", "transformers"],
      "pipeline_tag": "text-classification",
      "lastModified": "2024-01-15T10:30:00Z"
    },
    {
      "id": "cardiffnlp/twitter-roberta-base-sentiment",
      "author": "cardiffnlp",
      "downloads": 2100000,
      "likes": 543,
      "tags": ["text-classification", "pytorch", "transformers", "sentiment"],
      "pipeline_tag": "text-classification",
      "lastModified": "2024-01-10T08:15:00Z"
    }
  ],
  "totalCount": 2
}

Get Model Details

{
  "success": true,
  "model": {
    "id": "meta-llama/Llama-2-7b-hf",
    "author": "meta-llama",
    "sha": "abc123def456",
    "downloads": 5420000,
    "likes": 8932,
    "private": false,
    "tags": ["text-generation", "pytorch", "transformers", "llama", "safetensors"],
    "pipeline_tag": "text-generation",
    "library_name": "transformers",
    "modelCard": "Llama 2 is a collection of pretrained and fine-tuned generative text models...",
    "siblings": [
      {"rfilename": "config.json", "size": 1024},
      {"rfilename": "model.safetensors", "size": 13500000000},
      {"rfilename": "tokenizer.json", "size": 2500000}
    ],
    "createdAt": "2023-07-18T00:00:00Z",
    "lastModified": "2024-01-15T10:30:00Z"
  }
}

Search Datasets

{
  "success": true,
  "query": "instruction following",
  "datasets": [
    {
      "id": "tatsu-lab/alpaca",
      "author": "tatsu-lab",
      "downloads": 890000,
      "likes": 2341,
      "tags": ["text-generation", "instruction-following"],
      "lastModified": "2024-01-05T16:00:00Z"
    }
  ],
  "totalCount": 1
}

Trending Models

{
  "success": true,
  "trendingModels": [
    {"id": "mistralai/Mixtral-8x7B-Instruct-v0.1", "author": "mistralai", "likes": 4532, "downloads": 890000, "trend": "up"},
    {"id": "google/gemma-7b", "author": "google", "likes": 3421, "downloads": 654000, "trend": "up"},
    {"id": "Qwen/Qwen-72B-Chat", "author": "Qwen", "likes": 2987, "downloads": 432000, "trend": "up"}
  ]
}

Model Files

{
  "success": true,
  "repoId": "meta-llama/Llama-2-7b-hf",
  "files": [
    {"path": "config.json", "size": 1024, "type": "file"},
    {"path": "model.safetensors", "size": 13500000000, "type": "file"},
    {"path": "tokenizer.json", "size": 2500000, "type": "file"}
  ],
  "totalSize": 13502502048
}

Pricing (Pay-Per-Event)

Event	Description	Price
api_request	Per Hub API request	$0.01

Example costs:

• Search 50 model queries: 50 × $0.01 = $0.50
• Get 100 model details: 100 × $0.01 = $1.00
• Daily trending check (30 days): 30 × $0.01 = $0.30
• Demo mode: $0.00

Common Scenarios

Scenario 1: Find Best Model for Task

{
  "task": "search_models",
  "taskType": "text-classification",
  "library": "transformers",
  "sort": "downloads",
  "limit": 10,
  "demoMode": false
}

Scenario 2: Research Dataset Options

{
  "task": "search_datasets",
  "query": "code generation python",
  "sort": "downloads",
  "limit": 20,
  "demoMode": false
}

Scenario 3: Monitor Trending AI

{
  "task": "trending_models",
  "limit": 25,
  "webhookUrl": "https://hooks.zapier.com/...",
  "demoMode": false
}

Scenario 4: Evaluate Model Requirements

{
  "task": "list_model_files",
  "repoId": "stabilityai/stable-diffusion-xl-base-1.0",
  "demoMode": false
}

Webhook & Automation Integration

Zapier / Make.com / n8n

1. Create a webhook trigger
2. Copy the URL to webhookUrl
3. Process results in your workflow

Popular automations:

• Trending models -> Slack notification
• New datasets -> Research tracking sheet
• Model updates -> Team alerts
• Weekly AI digest -> Email newsletter

Hugging Face AI Suite

Actor	Best For
Hugging Face Master	Running inference on models
Hugging Face Text	Text model inference
Hugging Face Image	Image model inference
Hugging Face Audio	Audio model inference
Hugging Face Hub	Discovering models & datasets

FAQ

Q: Do I need an API token?

A: No for public repos and search. Yes for private repos or authenticated features.

Q: How often is trending data updated?

A: Hugging Face updates trending metrics multiple times daily.

Q: Can I access private models?

A: Yes, with an API token that has access to the private repo.

Q: What's the difference between downloads and likes?

A: Downloads = actual usage count. Likes = community appreciation. Both indicate popularity.

Q: How do I know which model to choose?

A: Sort by downloads for proven reliability, by likes for community preference, by trending for cutting-edge.

Common Problems & Solutions

"Repository not found"

• Check repo ID format: organization/model-name
• Verify repo exists and is public
• For private repos, provide valid API token

"Rate limit exceeded"

• Reduce request frequency
• Use API token for higher limits
• Cache results locally

"No results found"

• Broaden search terms
• Remove filters
• Check spelling

"Demo data showing"

• Set demoMode: false
• API token optional for public search

---

Built by John Rippy | Actor Arsenal