620 skills · sorted by relevance
Guides language model training with GRPO in TRL, comparing several responses and rewarding better results. Covers dataset preparation, scoring rules for correctness and format, training configuration, monitoring, and saving models for later use.
Build similarity search with FAISS to find nearby matches in large collections of numeric vectors. The skill guides index selection, memory reduction, GPU use, and saving indexes while balancing search speed and accuracy.
Prepare text for language models using HuggingFace Tokenizers, which splits text into model-readable units. Train custom vocabularies, process batches, track original text positions, and configure input lengths for use with transformers.
Train language models with SimPO using pairs of preferred and rejected answers. Configure preference training without a separate reference model, adapt settings for base or instruction models, and address unstable training, memory limits, or lost capabilities.
Get guidance on adapting large language models with Axolotl. Covers YAML configuration files, LoRA and QLoRA methods for training fewer parameters, distributed training settings, dataset formats, and debugging training code.
Guides setup and operation of Lambda Labs GPU instances for machine learning training and inference. Covers SSH access, persistent storage, API automation, and multi-GPU or multi-node training, including how to retain checkpoints and terminate idle instances.
Integrate the Gemini API on Agent Platform using the Google Gen AI SDK. Guidance covers authentication, text and multimedia tasks, structured JSON responses, live voice interactions, context caching, and batch prediction across five programming languages.
Get guidance on adapting LLMs with Unsloth, including implementation, API usage, and debugging. Covers LoRA and QLoRA, methods for adjusting models with fewer trainable parameters, with a focus on training speed and memory use.
Helps adapt LLMs to specific tasks with LLaMA-Factory, including training through a web interface and memory-saving methods such as QLoRA. Provides documentation references for learning features, implementing workflows, and investigating code problems.
Evaluate code generation models with HumanEval, MBPP, and other benchmarks. Test generated programs, compare models across programming languages, and record pass@k scores, which estimate the chance that at least one of k solutions passes the tests.
Train smaller language models using knowledge distillation, where a larger model supplies examples or prediction targets. This skill covers training losses, generated training data, parameter choices, and output comparisons to support model compression and specialized student models.
Manage cognee database migrations, from checking migration status and recovering blocked writes to creating schema or data updates. It also guides dataset backups, restores, and transfers using cognee’s portable COGX archive format.
Find and remove stored content from cognee using its SDK, HTTP API, or CLI. Inspect documents before deletion, choose document or dataset removal, or keep raw files while clearing derived graph relationships and search vectors.
Import text, files, URLs, repositories, and database content into cognee memory. This skill explains input handling, storage organization, extraction options, and cost estimates, while helping diagnose unsupported arguments and document update errors.
Route data analysis, large-file processing, and web retrieval through context-mode tools, returning only relevant results to the conversation. This helps preserve the context window, the limited amount of information an AI can work with at once.
Plan and analyze A/B tests, prepare tabular data, and train and evaluate prediction models. Estimate intervention effects from observational data, track model experiments with MLflow, and translate statistical findings into business decisions.
Design n8n automations for incoming events, API connections, database synchronization, AI agents, scheduled tasks, and batch processing. Choose a suitable structure, plan error handling, check connections, test results, and review performance when processing large numbers of items.
Prepare to fine-tune open models or Gemini models on Agent Platform. Check the environment, convert and validate training data, choose supported models and settings, and estimate tuning costs for open models.
Turn existing PromQL or ListTimeSeries queries into Cloud Monitoring chart definitions in textproto, a text format for Protocol Buffers. Generate readable titles, axis labels, units, and plot types, then validate the resulting widget files.
Develop varied ideas for names, writing angles, and problem solving by exploring five candidates internally and presenting the strongest. It also expands small example collections into diverse datasets for evaluation, training, or testing.
Configure OpenTelemetry to send AI application traces, records of execution steps, to Confident AI. Reuse existing exporters, choose the regional endpoint, and add AI-specific attributes without requiring the deepeval Python package.
Add DeepEval tracing to Python AI applications so execution steps appear in Confident AI. Choose a supported integration or manual @observe instrumentation, then capture inputs, outputs, step types, tags, and metadata.
Helps explore datasets, clean missing or inconsistent values, and explain patterns through statistics and charts. Uses Python and SQL to compare groups, examine relationships, and present findings in plain language with documented analysis steps.
Adapt large language models to specific tasks using LoRA and QLoRA, methods that train a small set of added parameters. Get guidance on preparing examples, choosing training settings, evaluating outputs, and saving or merging trained adapters.