Hugging Face
Official@huggingface · NYC + Paris
The AI community building the future.
Agent Skills by Hugging Face
Showing 46 vetted skills indexed across 6 GitHub repositories.
huggingfacecpu-kernels
Writes, optimizes, and benchmarks C++ CPU kernels with AVX2/AVX512 SIMD intrinsics for Hugging Face kernels.
huggingfacexpu-kernels
Generates and optimizes Triton kernels for Intel XPU GPUs through an iterative benchmark-driven workflow.
huggingfacetriton-kernels
Guides writing, testing, and benchmarking portable Triton GPU kernels for NVIDIA and AMD hardware.
huggingfacerocm-kernels
Write and benchmark optimized Triton kernels for AMD GPUs on ROCm.
huggingfacehf-cli
Manages Hugging Face Hub models, datasets, spaces, jobs, and endpoints via the hf CLI.
huggingfacetrl-training
Post-train LLMs with TRL trainers including SFT, DPO, GRPO, KTO, and reward modeling.
huggingfacehuggingface-papers
Fetch and process AI research papers from the Hugging Face Papers API.
huggingfacehuggingface-llm-trainer
Train language and vision models with TRL methods on Hugging Face Jobs.
huggingfacehuggingface-lora-space-builder
Generate Gradio web apps for AI models and publish them on Hugging Face Spaces.
huggingfacetransformers-js
Run Hugging Face machine learning models in JavaScript and TypeScript applications.
huggingfacehuggingface-community-evals
Evaluate Hugging Face Hub models locally with inspect-ai and lighteval.
huggingfacehf-cloud-sagemaker-iam-preflight
Verify or create AWS SageMaker IAM execution roles with AWS CLI.
huggingfacehuggingface-zerogpu
Manage AI/ML tasks on Hugging Face Spaces with ZeroGPU constraints.
huggingfacehf-cloud-sagemaker-deployment-planner
Automates AI model deployment to Amazon SageMaker with real-time, serverless, async options.
huggingfacehuggingface-spaces
Create and deploy ML apps on Hugging Face Spaces with Gradio, Docker, or Static.
huggingfacehuggingface-paper-publisher
Automate publishing and managing research papers on the Hugging Face Hub.
huggingfacehf-cloud-serving-image-selection
Select serving containers and retrieve image URIs for SageMaker deployments.
huggingfacetrain-sentence-transformers
Automate training and fine-tuning of sentence-transformers models for AI tasks.
huggingfacehuggingface-vision-trainer
Automate vision model training and fine-tuning on Hugging Face Jobs.
huggingfacehuggingface-tool-builder
Create reusable scripts for Hugging Face API data processing and retrieval.
huggingfacehuggingface-trackio
Log machine learning training metrics and fire alerts on specified conditions.
huggingfacehf-cloud-python-env-setup
Create an isolated Python environment with boto3 for SageMaker and AWS deployments.
huggingfacehuggingface-best
Recommend Hugging Face AI models by task, device, and benchmark scores.
huggingfacehuggingface-gradio
Build interactive web UIs for machine learning models with Gradio.
Frequently Asked Questions About Hugging Face
FAQPage SchemaWhat specific tasks can I perform using these capabilities?▼
You can train and fine-tune transformer models, deploy interactive web interfaces via Gradio, manage dataset metadata, and orchestrate model inference on cloud infrastructure like AWS SageMaker or local hardware using optimized formats like GGUF and MLX.
Which personas benefit most from these technical resources?▼
Machine learning engineers, research scientists, and infrastructure developers focused on model lifecycle management, distributed training, and production-grade deployment of neural networks will find these resources essential for streamlining their development cycles.
What are the primary prerequisites for deploying models to production?▼
Deployment requires an active Hugging Face account, configured AWS credentials for SageMaker integration, and sufficient compute resources. Users must also ensure their model weights are compatible with target runtime environments, such as Safetensors for inference or MLX for Apple Silicon.