30 skills · sorted by relevance
Fine-tune large language models — data curation, SFT, parameter-efficient methods (LoRA), evaluation, and avoiding common training failures. Use when a base model needs task-specific behavior or domain knowledge.
The English summary is being prepared. Showing the original description.
Retrieve up-to-date library, framework, and project documentation using scripts + MCP tools (Context7, Context Hub) with intelligent fallback. Use this skill whenever the user or agent needs documentation for any library, framework, API, SDK, or internal project spec. Triggers on "docs for [X]", "how does [library] work", "find documentation", "API reference for", "look up [feature] in [library]", "latest docs", "what's the API for", "find our [internal spec]", or any request that requires current, accurate documentation rather than relying on training data. Always prefer this skill over raw WebSearch for documentation retrieval — it returns structured, context-efficient results.
The English summary is being prepared. Showing the original description.
Orientação especializada para fine-tuning rápido com Unsloth - treinamento 2-5x mais rápido, 50-80% menos memória, otimização LoRA/QLoRA
The English summary is being prepared. Showing the original description.
This skill should be used at the start of any computationally intensive scientific task to detect and report available system resources (CPU cores, GPUs, memory, disk space). It creates a JSON file with resource information and strategic recommendations that inform computational approach decisions such as whether to use parallel processing (joblib, multiprocessing), out-of-core computing (Dask, Zarr), GPU acceleration (PyTorch, JAX), or memory-efficient strategies. Use this skill before running analyses, training models, processing large datasets, or any task where resource constraints matter.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
Patterns for loading PDE simulation datasets (PDEBench, PhiFlow, JAX-CFD) from HDF5 files. Handles layout detection (single tensor vs separate variables), spatial/temporal downsampling, multi-variable systems, HuggingFace and DaRUS data sources, and efficient PyTorch DataLoader creation. Use when preparing PDE data for neural operator training.
The English summary is being prepared. Showing the original description.