# Hugging Face MCP server

Connect to Hugging Face Hub and thousands of Gradio AI Applications

## Links
- Registry page: https://www.getdrio.com/mcp/co-huggingface-hf-mcp-server

## Install
- Endpoint: https://huggingface.co/mcp
- Auth: Auth required by registry metadata

## Setup notes
- Remote header: Authorization (secret)
- The upstream registry signals required auth or secrets.
- Remote endpoint: https://huggingface.co/mcp?login
- Remote endpoint: https://huggingface.co/mcp
- Header: Authorization

## Tools
- hf_whoami (Hugging Face User Info) - Inspect the current Hugging Face authentication context, including the account, visible organization memberships, and credential access details. Read-only and never returns credential values. Endpoint: https://huggingface.co/mcp
- hub_repo_search (Repo Search) - Search Hugging Face repositories with a shared query interface. You can target models, datasets, spaces, or aggregate across multiple repo types in one call. Include links to repositories in your response. Endpoint: https://huggingface.co/mcp
- hub_repo_details (Hub Repository Details) - Get details for one or more Hugging Face repos (model, dataset, or space). Auto-detects type unless specified. For datasets, use operations: overview, dataset_structure, dataset_preview. Use dataset_structure first to discover configs, splits, sizes, and schema. Use dataset_preview only when config and split are known, unless the dataset has a single config/split. Endpoint: https://huggingface.co/mcp
- hf_fs (Hugging Face Hub: Find, use and view models, datasets, spaces, buckets, papers, documentation and collections. Get daily papers reports, and browse trending content.) - Use to access the Hugging Face Hub. Navigate resources with ls, cat, attach, find, stat, and search over hf:// URIs. Roots: hf://models, hf://datasets, hf://spaces, hf://buckets, hf://collections, hf://papers, hf://docs. For papers, ls hf://papers/ARXIV_ID to discover related resources; cat hf://papers/ARXIV_ID/paper.md or metadata.json. Documentation paths include the current version from each product's llms.txt manifest.

Grammar; each token below is one args array element:
  ls     URI [(-R|-r|-lR|-laR|--recursive)] [(-l|-a|-la|-al|--long)] [--glob GLOB]
             [(-type|--type|--entry-type) TYPE] [--sort SORT] [(-limit|--limit) N]
  cat    URI [RELATIVE_PATH] [(-offset|--offset) N] [(-max-bytes|--max-bytes) N]
  attach URI [--max-bytes N]
  stat   URI [RELATIVE_PATH]
  find   URI [(-R|-r|--recursive)] [(-name|--name|--glob) GLOB] [(-path|--path) GLOB]
             [(-type|--type|--entry-type) TYPE] [(-limit|--limit) N]
  search URI [QUERY...] [(-type|--type|--entry-type) TYPE] [--sort SORT]
                        [--tag TAG] [--kind mcp] [(-limit|--limit) N]

TYPE = file|dir|repo|bucket|collection|paper|link.
Type aliases: f=file, d=dir, l=link, model|dataset|space=repo.
SORT = createdAt|downloads|likes|lastModified|likes30d|trendingScore|mainSize|id|trending|upvotes.
URI uses hf://, a typed shorthand such as models/OWNER/REPO, or a canonical https://huggingface.co URL. QUERY and GLOB are each one string token.
Search URI: hf://models|datasets|spaces[/OWNER], hf://collections[/OWNER], any hf://docs scope, or exactly hf://papers; not hf://.
Repository and collection searches may omit QUERY to browse or filter; documentation and paper searches require it.
Search joins multiple positional QUERY tokens with spaces. Cat and stat join one RELATIVE_PATH token to URI. Attach accepts exactly one complete URI and no RELATIVE_PATH or offset.
Discover before access: use search, ls, or find to locate targets; use stat when target type is uncertain; then reuse the returned URI, or the Target URI for links, verbatim.
Cat reads confirmed UTF-8 text files only. It rejects repositories, directories, model weights, archives, images, media, Parquet, and other binary content. Use stat for metadata instead.
Attach returns a complete JPEG, PNG, or WebP repository or bucket file as image content. It classifies only by file extension, never truncates, and has a default and hard limit of 4 MiB; --max-bytes may only lower it.
Find recursively matches names and paths within an owner namespace, repository, or supported documentation scope. Use search—not an unscoped find—for global repository, collection, documentation, paper, or Space discovery.
Long-list flags are accepted for compatibility; hf_fs listings are already structured, so they do not alter output.
Find is already recursive, so recursive flags are accepted without altering behavior.
Space search: hf://spaces uses semantic search; repeat --tag to require tags, or use --kind mcp for --tag mcp-server. hf://spaces/OWNER uses owner-scoped keyword search.
Documentation: ls hf://docs for products; search any docs scope; use returned hf:// URIs verbatim.
Trending listings: ls hf://models/trending, hf://datasets/trending, or hf://spaces/trending. They return up to 20 entries.
Trending paths imply trending order; --sort trending|trendingScore is redundant but valid.
Trending papers: ls hf://papers/trending.
Sort is route-specific: use it with search or supported owner/collection listings, never with repository file listings or documentation. For global trending repositories, use the /trending listing URI.
TYPE filters mixed results; omit it when the URI already fixes the result type.
Limits and path-specific behavior are documented at hf://README.md.
Omit --limit and --sort unless the request asks for a cap, ordering, or exhaustive results.
No pipes, redirects, shell expansion, or multiple commands. Endpoint: https://huggingface.co/mcp

## Resources
- skill://hf-cli/SKILL.md - Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging Face Hub. Use when: handling authentication; managing local cache; managing Hugging Face Buckets; running or scheduling jobs on Hugging Face infrastructure; managing Hugging Face repos; discussions and pull requests; browsing models, datasets and spaces; reading, searching, or browsing academic papers; managing collections; querying datasets; configuring spaces; setting up webhooks; or deploying and managing HF Inference Endpoints. Make sure to use this skill whenever the user mentions 'hf', 'huggingface', 'Hugging Face', 'huggingface-cli', or 'hugging face cli', or wants to do anything related to the Hugging Face ecosystem and to AI and ML in general. Also use for cloud storage needs like training checkpoints, data pipelines, or agent traces. Use even if the user doesn't explicitly ask for a CLI command. Replaces the deprecated `huggingface-cli`. MIME type: text/markdown
- skill://hf-cloud-aws-context-discovery/SKILL.md - Discover the user's local AWS context (active profile, region, account ID, caller identity) at the start of any AWS task. Use this skill before any other AWS work — deploying to SageMaker, creating resources, calling AWS APIs, or anything that touches an AWS account. Use it especially when the user has not specified a region or profile explicitly, when they say things like "use my AWS account", "deploy to AWS", "use my profile", or when about to make any AWS CLI or SDK call. Never guess the region or account ID — always use this skill to read it from the local configuration first. MIME type: text/markdown
- skill://hf-cloud-python-env-setup/SKILL.md - Set up an isolated Python environment for SageMaker / AWS work, with the right Python version and current boto3. Use this skill whenever Python code will be executed for a SageMaker deployment, training job, or any AWS automation — including when about to run `pip install`, when about to invoke `boto3`, when creating or activating a virtualenv, or when the user asks to "set up the environment". Never use system Python and never `pip install` into it. Always isolate. This skill prevents the most common failure modes: wrong Python version, dependency conflicts, and stale SDKs. MIME type: text/markdown
- skill://hf-cloud-python-env-setup/requirements.txt - MIME type: text/plain
- skill://hf-cloud-python-env-setup/scripts/check_versions.py - MIME type: text/x-python
- skill://hf-cloud-python-env-setup/scripts/setup_env.py - MIME type: text/x-python
- skill://hf-cloud-sagemaker-deployment-planner/SKILL.md - Plan and coordinate the deployment of a model to Amazon SageMaker AI. Use this skill whenever the user wants to deploy, host, serve, or expose a model on SageMaker or AWS — including phrases like "deploy a model", "host this LLM on AWS", "serve this embedding model", "deploy a reranker", "deploy a text-to-image / diffusion model", "host this for async inference", "create an endpoint", "serve my fine-tuned model", or any request that involves making a model available for inference on AWS. Use this even when the user is vague (e.g. "I just want to get this running on AWS, you figure it out"). Works for text-generation LLMs, embedding models, rerankers, classifiers, text-to-image / diffusion models — picks the right serving stack and chooses between real-time and async inference. This is the entry-point skill for SageMaker deployment work — it asks clarifying questions, picks a deployment pathway, and coordinates the other deployment skills. MIME type: text/markdown
- skill://hf-cloud-sagemaker-iam-preflight/SKILL.md - Ensure a usable SageMaker execution role exists before deploying or training. Use this skill whenever about to create a SageMaker endpoint, model, training job, or any resource that requires an execution role. Use it especially when the user has not provided a role ARN explicitly, when scripts are about to call `iam:CreateRole`, or when an AccessDenied error mentions an IAM action. Never blindly call `iam:CreateRole` — always check for existing roles first. This skill prevents the most common SageMaker deployment failure: trying to create IAM resources from an SSO principal that has no IAM write permissions. MIME type: text/markdown
- skill://hf-cloud-sagemaker-iam-preflight/references/minimum-permissions.json - MIME type: application/json
- skill://hf-cloud-sagemaker-iam-preflight/references/trust-policy.json - MIME type: application/json
- skill://hf-cloud-sagemaker-iam-preflight/scripts/check_role.py - MIME type: text/x-python
- skill://hf-cloud-sagemaker-iam-preflight/scripts/create_role.py - MIME type: text/x-python
- skill://hf-cloud-sagemaker-production-defaults/SKILL.md - Create a SageMaker endpoint (real-time, real-time scale-to-zero, or async) with autoscaling, CloudWatch alarms, and tagging enabled by default. Use this skill whenever about to create a SageMaker endpoint, write deployment code that calls `create_endpoint`, or finalize a deployment after the image URI and IAM role are known. Provides deploy.py for real-time endpoints, deploy_ic.py for real-time endpoints that scale to zero instances via inference components, and deploy_async.py for async endpoints (also scale-to-zero). This is the last step in the SageMaker deployment workflow. Never generate a bare `create_endpoint` call without these defaults — endpoints without autoscaling or alarms are demos, not deployments. MIME type: text/markdown
- skill://hf-cloud-sagemaker-production-defaults/references/deployment-template.md - MIME type: text/markdown
- skill://hf-cloud-sagemaker-production-defaults/scripts/_common.py - MIME type: text/x-python
- skill://hf-cloud-sagemaker-production-defaults/scripts/deploy.py - MIME type: text/x-python
- skill://hf-cloud-sagemaker-production-defaults/scripts/deploy_async.py - MIME type: text/x-python
- skill://hf-cloud-sagemaker-production-defaults/scripts/deploy_ic.py - MIME type: text/x-python
- skill://hf-cloud-sagemaker-production-defaults/scripts/invoke_endpoint.py - MIME type: text/x-python
- skill://hf-cloud-sagemaker-production-defaults/scripts/teardown.py - MIME type: text/x-python
- skill://hf-cloud-serving-image-selection/SKILL.md - Pick the right serving container for a SageMaker model deployment and find its current image URI. Use this skill whenever about to deploy a model to a SageMaker endpoint and an image URI needs to be chosen — including when the user says "deploy this LLM", "host this HuggingFace model", "serve this fine-tuned model", "deploy this embedding model", "host a reranker", "serve a sentence-transformers model", or when about to hardcode any container URI in deployment code. HuggingFace-curated Deep Learning Containers are ALWAYS preferred: HuggingFace vLLM (LLMs and generative rerankers), HuggingFace vLLM-Omni (multimodal), TEI (embeddings/cross-encoder rerankers), HF Inference Toolkit (other transformers). Generic images (AWS vLLM, DJL-LMI, SGLang) are used only when no HuggingFace image is compatible — never merely because they carry a newer version. Never hardcode a container URI from memory and never default to TGI. Prevents stale-image failures and wrong-region URIs. MIME type: text/markdown
- skill://hf-cloud-serving-image-selection/references/model-to-image.md - MIME type: text/markdown
- skill://hf-cloud-serving-image-selection/scripts/mirror_image.py - MIME type: text/x-python
- skill://hf-mem/SKILL.md - Hugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Hugging Face Hub MIME type: text/markdown
- skill://huggingface-best/SKILL.md - Use when the user asks about finding the best, top, or recommended model for a task, wants to know what AI model to use, or wants to compare models by benchmark scores. Triggers on: "best model for X", "what model should I use for", "top models for [task]", "which model runs on my laptop/machine/device", "recommend a model for", "what LLM should I use for", "compare models for", "what's state of the art for", or any question about choosing an AI model for a specific use case. Always use this skill when the user wants model recommendations or comparisons, even if they don't explicitly mention HuggingFace or benchmarks. MIME type: text/markdown
- skill://huggingface-community-evals/SKILL.md - Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestration, model-card PRs, .eval_results publication, or community-evals automation. MIME type: text/markdown
- skill://huggingface-community-evals/examples/.env.example - MIME type: application/octet-stream
- skill://huggingface-community-evals/examples/USAGE_EXAMPLES.md - MIME type: text/markdown
- skill://huggingface-community-evals/scripts/inspect_eval_uv.py - MIME type: text/x-python
- skill://huggingface-community-evals/scripts/inspect_vllm_uv.py - MIME type: text/x-python
- skill://huggingface-community-evals/scripts/lighteval_vllm_uv.py - MIME type: text/x-python
- skill://huggingface-datasets/SKILL.md - Use this skill for Hugging Face Dataset Viewer API workflows that fetch subset/split metadata, paginate rows, search text, apply filters, download parquet URLs, and read size or statistics. MIME type: text/markdown
- skill://huggingface-gradio/SKILL.md - Build Gradio web UIs and demos in Python. Use when creating or editing Gradio apps, components, event listeners, layouts, or chatbots. MIME type: text/markdown
- skill://huggingface-gradio/examples.md - MIME type: text/markdown
- skill://huggingface-llm-trainer/SKILL.md - Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, model selection/leaderboards and model persistence. Use for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup. MIME type: text/markdown
- skill://huggingface-llm-trainer/references/gguf_conversion.md - MIME type: text/markdown
- skill://huggingface-llm-trainer/references/hardware_guide.md - MIME type: text/markdown
- skill://huggingface-llm-trainer/references/hub_saving.md - MIME type: text/markdown
- skill://huggingface-llm-trainer/references/local_training_macos.md - MIME type: text/markdown
- skill://huggingface-llm-trainer/references/reliability_principles.md - MIME type: text/markdown
- skill://huggingface-llm-trainer/references/trackio_guide.md - MIME type: text/markdown
- skill://huggingface-llm-trainer/references/training_methods.md - MIME type: text/markdown
- skill://huggingface-llm-trainer/references/training_patterns.md - MIME type: text/markdown
- skill://huggingface-llm-trainer/references/troubleshooting.md - MIME type: text/markdown
- skill://huggingface-llm-trainer/references/unsloth.md - MIME type: text/markdown
- skill://huggingface-llm-trainer/scripts/convert_to_gguf.py - MIME type: text/x-python
- skill://huggingface-llm-trainer/scripts/dataset_inspector.py - MIME type: text/x-python
- skill://huggingface-llm-trainer/scripts/estimate_cost.py - MIME type: text/x-python
- skill://huggingface-llm-trainer/scripts/hf_benchmarks.py - MIME type: text/x-python
- skill://huggingface-llm-trainer/scripts/train_dpo_example.py - MIME type: text/x-python
- skill://huggingface-llm-trainer/scripts/train_grpo_example.py - MIME type: text/x-python
- skill://huggingface-llm-trainer/scripts/train_sft_example.py - MIME type: text/x-python
- skill://huggingface-llm-trainer/scripts/unsloth_sft_example.py - MIME type: text/x-python
- skill://huggingface-local-models/SKILL.md - Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conversion, and OpenAI-compatible local serving. MIME type: text/markdown
- skill://huggingface-local-models/references/hardware.md - MIME type: text/markdown
- skill://huggingface-local-models/references/hub-discovery.md - MIME type: text/markdown
- skill://huggingface-local-models/references/quantization.md - MIME type: text/markdown
- skill://huggingface-lora-space-builder/SKILL.md - Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA. Use when someone asks to create, generate, ship, or publish a Space, demo, Gradio app, or playground for a LoRA — including LoRAs for Qwen-Image, Qwen-Image-Edit, LTX-Video, Wan, FLUX, SDXL, or other diffusion base models. Also triggers when someone describes a LoRA they trained or hosts on the Hub and wants to share it. Covers picking the right base pipeline and `diffusers` inference recipe, designing a UI tailored to the LoRA's task and inputs (Union/multi-task control, edit, video, image, etc.), respecting model-card recommendations (trigger words, steps, guidance, LoRA scale, example inputs), and shipping to ZeroGPU hardware as a private Space by default. MIME type: text/markdown
- skill://huggingface-lora-space-builder/references/adapting-to-the-lora.md - MIME type: text/markdown
- skill://huggingface-lora-space-builder/references/base-models/krea-2.md - MIME type: text/markdown
- skill://huggingface-lora-space-builder/references/base-models/ltx.md - MIME type: text/markdown
- skill://huggingface-lora-space-builder/references/base-models/qwen-image.md - MIME type: text/markdown
- skill://huggingface-lora-space-builder/references/creative-mode.md - MIME type: text/markdown
- skill://huggingface-lora-space-builder/references/tasks.md - MIME type: text/markdown
- skill://huggingface-lora-space-builder/references/zerogpu-and-publishing.md - MIME type: text/markdown
- skill://huggingface-paper-publisher/SKILL.md - Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles. MIME type: text/markdown
- skill://huggingface-paper-publisher/examples/example_usage.md - MIME type: text/markdown
- skill://huggingface-paper-publisher/references/quick_reference.md - MIME type: text/markdown
- skill://huggingface-paper-publisher/scripts/paper_manager.py - MIME type: text/x-python
- skill://huggingface-paper-publisher/templates/arxiv.md - MIME type: text/markdown
- skill://huggingface-paper-publisher/templates/ml-report.md - MIME type: text/markdown
- skill://huggingface-paper-publisher/templates/modern.md - MIME type: text/markdown
- skill://huggingface-paper-publisher/templates/standard.md - MIME type: text/markdown
- skill://huggingface-papers/SKILL.md - Look up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata such as authors, linked models/datasets/spaces, Github repo and project page. Use when the user shares a Hugging Face paper page URL, an arXiv URL or ID, or asks to summarize, explain, or analyze an AI research paper. MIME type: text/markdown
- skill://huggingface-spaces/README.md - MIME type: text/markdown
- skill://huggingface-spaces/SKILL.md - Build, deploy, and maintain applications on Hugging Face Spaces — Gradio / Docker / Static SDKs, ZeroGPU and dedicated hardware, model loading, debugging, buckets, inference providers, community grants. Use whenever the user asks to create or host an app on Hugging Face, port code onto ZeroGPU, fix a Space that won't build or run, or otherwise work with `hf spaces …`, `@spaces.GPU`, Space README frontmatter, or the `spaces` Python package. MIME type: text/markdown
- skill://huggingface-spaces/references/3d-cuda-extensions.md - MIME type: text/markdown
- skill://huggingface-spaces/references/3d-generation.md - MIME type: text/markdown
- skill://huggingface-spaces/references/3d-gsplat.md - MIME type: text/markdown
- skill://huggingface-spaces/references/3d-models.md - MIME type: text/markdown
- skill://huggingface-spaces/references/3d-outputs.md - MIME type: text/markdown
- skill://huggingface-spaces/references/buckets.md - MIME type: text/markdown
- skill://huggingface-spaces/references/debugging.md - MIME type: text/markdown
- skill://huggingface-spaces/references/gradio.md - MIME type: text/markdown
- skill://huggingface-spaces/references/grants.md - MIME type: text/markdown
- skill://huggingface-spaces/references/inference-providers.md - MIME type: text/markdown
- skill://huggingface-spaces/references/known-errors.md - MIME type: text/markdown
- skill://huggingface-spaces/references/requirements.md - MIME type: text/markdown
- skill://huggingface-spaces/references/zerogpu.md - MIME type: text/markdown
- skill://huggingface-tool-builder/SKILL.md - Use this skill when the user wants to build tool/scripts or achieve a task where using data from the Hugging Face API would help. This is especially useful when chaining or combining API calls or the task will be repeated/automated. This Skill creates a reusable script to fetch, enrich or process data. MIME type: text/markdown
- skill://huggingface-tool-builder/references/baseline_hf_api.py - MIME type: text/x-python
- skill://huggingface-tool-builder/references/baseline_hf_api.sh - MIME type: application/x-sh
- skill://huggingface-tool-builder/references/baseline_hf_api.tsx - MIME type: text/x-typescript
- skill://huggingface-tool-builder/references/find_models_by_paper.sh - MIME type: application/x-sh
- skill://huggingface-tool-builder/references/hf_enrich_models.sh - MIME type: application/x-sh
- skill://huggingface-tool-builder/references/hf_model_card_frontmatter.sh - MIME type: application/x-sh
- skill://huggingface-tool-builder/references/hf_model_papers_auth.sh - MIME type: application/x-sh
- skill://huggingface-trackio/SKILL.md - Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API), firing alerts for training diagnostics, or retrieving/analyzing logged metrics (CLI). Supports real-time dashboard visualization, alerts with webhooks, HF Space syncing, and JSON output for automation. MIME type: text/markdown
- skill://huggingface-trackio/references/alerts.md - MIME type: text/markdown
- skill://huggingface-trackio/references/logging_metrics.md - MIME type: text/markdown
- skill://huggingface-trackio/references/retrieving_metrics.md - MIME type: text/markdown
- skill://huggingface-vision-trainer/SKILL.md - Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation, Trackio monitoring, and Hub persistence. Use when users mention training object detection, image classification, SAM, SAM2, segmentation, image matting, DETR, D-FINE, RT-DETR, ViT, timm, MobileNet, ResNet, bounding box models, or fine-tuning vision models on Hugging Face Jobs. MIME type: text/markdown
- skill://huggingface-vision-trainer/references/finetune_sam2_trainer.md - MIME type: text/markdown
- skill://huggingface-vision-trainer/references/hub_saving.md - MIME type: text/markdown
- skill://huggingface-vision-trainer/references/image_classification_training_notebook.md - MIME type: text/markdown
- skill://huggingface-vision-trainer/references/object_detection_training_notebook.md - MIME type: text/markdown
- skill://huggingface-vision-trainer/references/reliability_principles.md - MIME type: text/markdown
- skill://huggingface-vision-trainer/references/timm_trainer.md - MIME type: text/markdown
- skill://huggingface-vision-trainer/scripts/dataset_inspector.py - MIME type: text/x-python
- skill://huggingface-vision-trainer/scripts/estimate_cost.py - MIME type: text/x-python
- skill://huggingface-vision-trainer/scripts/image_classification_training.py - MIME type: text/x-python
- skill://huggingface-vision-trainer/scripts/object_detection_training.py - MIME type: text/x-python
- skill://huggingface-vision-trainer/scripts/sam_segmentation_training.py - MIME type: text/x-python
- skill://huggingface-zerogpu/SKILL.md - AI demos and GPU compute with Gradio Spaces and Hugging Face Spaces ZeroGPU. Use when writing or reviewing code that uses `@spaces.GPU`, configuring `python_version` or `requirements.txt` for a ZeroGPU Space, or handling ZeroGPU-specific code constraints — pickle-based process isolation, `gr.State` semantics across the worker boundary, no `torch.compile` (use AoTI instead), CUDA wheel-only builds (no `nvcc` at build or runtime), large vs xlarge sizing, and dynamic duration callables. Make sure to use this skill whenever the user mentions ZeroGPU, `@spaces.GPU`, or the `spaces` Python package, or hits ZeroGPU-specific code errors like `PicklingError` across the worker boundary, `illegal duration`, or `flash-attn` wheel-build failures — even when the user does not explicitly ask for ZeroGPU coding guidance. Trigger on `import spaces` or `@spaces.GPU` in code. MIME type: text/markdown
- skill://huggingface-zerogpu/references/concurrency.md - MIME type: text/markdown
- skill://huggingface-zerogpu/references/cuda-and-deps.md - MIME type: text/markdown
- skill://huggingface-zerogpu/references/how-quota-works.md - MIME type: text/markdown
- skill://huggingface-zerogpu/references/how-zerogpu-works.md - MIME type: text/markdown
- skill://train-sentence-transformers/SKILL.md - Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder; dense or static embedding model; for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker; pair scoring for two-stage retrieval / pair classification), and `SparseEncoder` (SPLADE, sparse embedding model; for learned-sparse retrieval). Covers loss selection, hard-negative mining, evaluators, distillation, LoRA, Matryoshka, and Hugging Face Hub publishing. Use for any sentence-transformers training task. MIME type: text/markdown
- skill://train-sentence-transformers/references/base_model_selection.md - MIME type: text/markdown
- skill://train-sentence-transformers/references/dataset_formats.md - MIME type: text/markdown
- skill://train-sentence-transformers/references/evaluators_cross_encoder.md - MIME type: text/markdown
- skill://train-sentence-transformers/references/evaluators_sentence_transformer.md - MIME type: text/markdown
- skill://train-sentence-transformers/references/evaluators_sparse_encoder.md - MIME type: text/markdown
- skill://train-sentence-transformers/references/hardware_guide.md - MIME type: text/markdown
- skill://train-sentence-transformers/references/hf_jobs_execution.md - MIME type: text/markdown
- skill://train-sentence-transformers/references/losses_cross_encoder.md - MIME type: text/markdown
- skill://train-sentence-transformers/references/losses_sentence_transformer.md - MIME type: text/markdown
- skill://train-sentence-transformers/references/losses_sparse_encoder.md - MIME type: text/markdown
- skill://train-sentence-transformers/references/model_architectures.md - MIME type: text/markdown
- skill://train-sentence-transformers/references/prompts_and_instructions.md - MIME type: text/markdown
- skill://train-sentence-transformers/references/training_args.md - MIME type: text/markdown
- skill://train-sentence-transformers/references/troubleshooting.md - MIME type: text/markdown
- skill://train-sentence-transformers/scripts/mine_hard_negatives.py - MIME type: text/x-python
- skill://train-sentence-transformers/scripts/train_cross_encoder_distillation_example.py - MIME type: text/x-python
- skill://train-sentence-transformers/scripts/train_cross_encoder_example.py - MIME type: text/x-python
- skill://train-sentence-transformers/scripts/train_cross_encoder_listwise_example.py - MIME type: text/x-python
- skill://train-sentence-transformers/scripts/train_sentence_transformer_distillation_example.py - MIME type: text/x-python
- skill://train-sentence-transformers/scripts/train_sentence_transformer_example.py - MIME type: text/x-python
- skill://train-sentence-transformers/scripts/train_sentence_transformer_make_multilingual_example.py - MIME type: text/x-python
- skill://train-sentence-transformers/scripts/train_sentence_transformer_matryoshka_example.py - MIME type: text/x-python
- skill://train-sentence-transformers/scripts/train_sentence_transformer_multi_dataset_example.py - MIME type: text/x-python
- skill://train-sentence-transformers/scripts/train_sentence_transformer_static_embedding_example.py - MIME type: text/x-python
- skill://train-sentence-transformers/scripts/train_sentence_transformer_with_lora_example.py - MIME type: text/x-python
- skill://train-sentence-transformers/scripts/train_sparse_encoder_distillation_example.py - MIME type: text/x-python
- skill://train-sentence-transformers/scripts/train_sparse_encoder_example.py - MIME type: text/x-python
- skill://transformers-js/SKILL.md - Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image classification, object detection), audio (speech recognition, audio classification), and multimodal tasks. Works in browsers and server-side runtimes (Node.js, Bun, Deno) with WebGPU/WASM using pre-trained models from Hugging Face Hub. MIME type: text/markdown
- skill://transformers-js/references/CACHE.md - MIME type: text/markdown
- skill://transformers-js/references/CONFIGURATION.md - MIME type: text/markdown
- skill://transformers-js/references/EXAMPLES.md - MIME type: text/markdown
- skill://transformers-js/references/MODEL_ARCHITECTURES.md - MIME type: text/markdown
- skill://transformers-js/references/MODEL_REGISTRY.md - MIME type: text/markdown
- skill://transformers-js/references/PIPELINE_OPTIONS.md - MIME type: text/markdown
- skill://transformers-js/references/TEXT_GENERATION.md - MIME type: text/markdown
- skill://trl-training/SKILL.md - Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning). Supports SFT, DPO, GRPO, KTO, RLOO and Reward Model training via CLI commands. MIME type: text/markdown

## Prompts
Not captured

## Metadata
- Owner: co.huggingface
- Version: 0.2.33
- Runtime: Streamable Http
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Oct 22, 2025
- Source: https://registry.modelcontextprotocol.io