huggingface/skills
Give your agents the power of the Hugging Face ecosystem
https://skillcdn.ai/gh/huggingface/skillsConnect this address to your AI to use these skills. How to connect
- Default branch
main - Commit
25910b3 - License
Apache-2.0 - Searchwords and meaning
Explore this repository
Searches the original text of skills and documents by words and by meaning; display translations are not searched.
Documents
- GGUF Conversion GuideAfter training models with TRL on Hugging Face Jobs, convert them to GGUF format for use with llama.cpp, Ollama, LM Studio, and other local inference tools.skills/huggingface-llm-trainer/references/gguf_conversion.md
- Hardware Selection GuideChoosing the right hardware (flavor) is critical for cost-effective training.skills/huggingface-llm-trainer/references/hardware_guide.md
- Saving Training Results to Hugging Face Hub⚠️ CRITICAL: Training environments are ephemeral. ALL results are lost when a job completes unless pushed to the Hub.skills/huggingface-llm-trainer/references/hub_saving.md
- Local Training on macOS (Apple Silicon)Run small LoRA fine-tuning jobs locally on Mac for smoke tests and quick iteration before submitting to HF Jobs.skills/huggingface-llm-trainer/references/local_training_macos.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-llm-trainer/references/reliability_principles.md
- Trackio Integration for TRL TrainingTrackio is an experiment tracking library that provides real-time metrics visualization for remote training on Hugging Face Jobs infrastructure.skills/huggingface-llm-trainer/references/trackio_guide.md
- TRL Training Methods OverviewTRL (Transformer Reinforcement Learning) provides multiple training methods for fine-tuning and aligning language models. This reference provides a brief overview of each method.skills/huggingface-llm-trainer/references/training_methods.md
- Common Training PatternsThis guide provides common training patterns and use cases for TRL on Hugging Face Jobs.skills/huggingface-llm-trainer/references/training_patterns.md
- Troubleshooting TRL Training JobsCommon issues and solutions when training with TRL on Hugging Face Jobs.skills/huggingface-llm-trainer/references/troubleshooting.md
- Unsloth: Fast Fine-Tuning with Memory OptimizationUnsloth is a fine-tuning library that provides ~2x faster training and ~60% less VRAM usage for LLM training. It's particularly useful when working with limited GPU memory or when speed is critical.skills/huggingface-llm-trainer/references/unsloth.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, ...)