huggingface/skills

Give your agents the power of the Hugging Face ecosystem

https://skillcdn.ai/gh/huggingface/skills

Connect this address to your AI to use these skills. How to connect

Default branchmain
Commit25910b3
LicenseApache-2.0
Searchwords and meaning

View on GitHub

Explore this repository

Searches the original text of skills and documents by words and by meaning; display translations are not searched.

Documents

Fine-tuning SAM2 with HF TrainerFine-tune SAM2.1 on a small part of the MicroMat dataset for image matting, using the Hugging Face Trainer with a custom loss function.skills/huggingface-vision-trainer/references/finetune_sam2_trainer.md
Saving Vision Models to Hugging Face HubCRITICAL: Training environments are ephemeral. ALL results are lost when a job completes unless pushed to the Hub.skills/huggingface-vision-trainer/references/hub_saving.md
Image classificationImage classification assigns a label or class to an image. Unlike text or audio classification, the inputs are the pixel values that comprise an image. There are many applications for image classific…skills/huggingface-vision-trainer/references/image_classification_training_notebook.md
Object Detection Training ReferenceObject detection is the computer vision task of detecting instances (such as humans, buildings, or cars) in an image. Object detection models receive an image as input and output coordinates of the b…skills/huggingface-vision-trainer/references/object_detection_training_notebook.md
Reliability Principles for Training JobsThese principles are derived from real production failures and successful fixes. Following them prevents common failure modes and ensures reliable job execution.skills/huggingface-vision-trainer/references/reliability_principles.md
Using timm models with Hugging Face TrainerTransformers has first-class support for timm models via the TimmWrapper classes. You can load any timm model and use it directly with the Trainer API for image classification. Here's how it works:skills/huggingface-vision-trainer/references/timm_trainer.md

Skipped (3)

These manifests were not served. Fix them and push: the next commit is indexed again.

skills/huggingface-trackio/references/retrieving_metrics.mdlink_missing2 links name no file of the repository (docs/source/cli_commands.md, docs/source/api_mcp_server.md)
skills/huggingface-vision-trainer/references/image_classification_training_notebook.mdlink_missing9 links name no file of the repository (../model_doc/vit, /docs/transformers/v5.2.0/en/main_classes/data_collator#transformers.DefaultDataCollator, /docs/transformers/v5.2.0/en/main_classes/trainer#transformers.Trainer, ...)
skills/huggingface-vision-trainer/references/object_detection_training_notebook.mdlink_missing6 links name no file of the repository (/docs/transformers/v5.1.0/en/model_doc/auto#transformers.AutoImageProcessor, /docs/transformers/v5.1.0/en/main_classes/trainer#transformers.Trainer, /docs/transformers/v5.1.0/en/model_doc/auto#transformers.AutoModelForObjectDetection, ...)