AI Skills for Hugging Face

Use this skill when users need to search for datasets, download data files, or explore data repositories. Triggers include: requests to \"find datasets\", \"search for data\", \"download dataset from Kaggle\", \"get data from Hugging Face\", \"find ML datasets\", or mentions of data repositories ...

Send high-quality text-to-speech voice messages on WhatsApp in 40+ languages with automatic delivery

Two-layer content safety for agent input and output. Use when (1) a user message attempts to override, ignore, or bypass previous instructions (prompt injection), (2) a user message references system prompts, hidden instructions, or internal configuration, (3) receiving messages from untrusted us...

Advanced expert in prompt engineering, custom instructions design, and prompt optimization for AI agents

Speech-To-Text with MLX (Apple Silicon) and opensource models (default GLM-ASR-Nano-2512) locally.

Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.

Semantic image-text matching with CLIP and alternatives. Use for image search, zero-shot classification, similarity matching. NOT for counting objects, fine-grained classification (celebrities, car models), spatial reasoning, or compositional queries. Activate on "CLIP", "embeddings", "image simi...

This skill provides guidance for counting tokens in datasets using specific tokenizers. It should be used when tasks involve tokenizing dataset content, filtering data by domain or category, and aggregating token counts. Common triggers include requests to count tokens in HuggingFace datasets, fi...

Create, clean, and optimize datasets for LLM fine-tuning. Covers formats (Alpaca, ShareGPT, ChatML), synthetic data generation, quality assessment, and augmentation. Use when preparing data for training.

Expert guidance for Meta's FAIRChem library - machine learning methods for materials science and quantum chemistry using pretrained UMA models with ASE integration for fast, accurate predictions

Generate images for PDF test fixtures using HuggingFace FLUX.1-schnell (FREE). Supports AI generation, mermaid diagrams, and placeholder images.

Generate high-quality training datasets from documents, text corpora, and structured content. Use when creating AI training data from dictionaries, documents, or when generating examples for machine learning models. Optimized for low-resource languages and domain-specific knowledge extraction.

Best practices for the Common utilities package in LlamaFarm. Covers HuggingFace Hub integration, GGUF model management, and shared utilities.

Generate comprehensive model cards and upload fine-tuned models to Hugging Face Hub with professional documentation

Use when training a fine-tuned model and evaluating improvement over base model. Triggers - have filtered training data, ready to submit training job, need to convert to GGUF. Requires finetune-generate first.

Training manager for Hugging Face Jobs - launch fine-tuning on HF cloud GPUs with optional WandB monitoring

Copilot agent that assists with machine learning model development, training, evaluation, deployment, and MLOps Trigger terms: machine learning, ML, AI, model training, MLOps, model deployment, feature engineering, model evaluation, neural network, deep learning Use when: User requests involve ...