140 skills · sorted by relevance
Process large email, document, and transcript archives by routing items to AI models according to their importance. Rule-based privacy checks run before model calls, while extracted information becomes linked knowledge pages with progress checkpoints.
Guide large language model training with OpenRLHF using human preference feedback. Covers training method selection, distributed GPU setup, reward model training, and memory tuning, with examples for PPO, GRPO, and DPO.
Guides experiments that inspect and modify internal values in PyTorch models to study their effects on predictions. Covers local analysis and remote experiments through NDIF for models too large for local GPUs.
Applies the engineering and research philosophies of Jeff Dean, Chief Scientist at Google DeepMind and Google Research. Reach for this skill whenever you are designing large-scale distributed systems, optimizing latency and energy efficiency, or making architectural decisions about machine learning infrastructure. It should trigger automatically for topics involving hardware-ML co-design, model distillation, sparse activation, massively multi-task models, or scaling systems by 5x to 10x. Use this skill to evaluate system bottlenecks, transition from specialized to unified models, and optimize experimental velocity. Apply his mental models to avoid premature 100x scaling and to treat AI models as reasoning engines rather than memorization databases.
The English summary is being prepared. Showing the original description.
Applies the engineering and research philosophies of Jeff Dean, Chief Scientist at Google DeepMind and Google Research. Reach for this skill whenever you are designing large-scale distributed systems, optimizing latency and energy efficiency, or making architectural decisions about machine learning infrastructure. It should trigger automatically for topics involving hardware-ML co-design, model distillation, sparse activation, massively multi-task models, or scaling systems by 5x to 10x. Use this skill to evaluate system bottlenecks, transition from specialized to unified models, and optimize experimental velocity. Apply his mental models to avoid premature 100x scaling and to treat AI models as reasoning engines rather than memorization databases.
The English summary is being prepared. Showing the original description.
Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.
The English summary is being prepared. Showing the original description.
Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.
The English summary is being prepared. Showing the original description.
Design dbt data transformations with clearly organized models, data quality tests, documentation, and incremental processing that updates only part of a dataset. Use it to structure analytics tables and organize a dbt project.
Evaluate language models with over 100 benchmark tests covering knowledge, math, coding, safety, and image understanding. Configure runs on Docker, Slurm computing clusters, or cloud infrastructure, compare models, and export results.
Fine-tune large language models with LoRA and QLoRA while limiting GPU memory use. Guides training settings and adapter management, using small sets of task-specific weights that can be saved, switched, or merged into a base model.
Configure LLM inference and serving on NVIDIA GPUs with TensorRT-LLM. Covers quantization, which reduces numerical precision, batching requests during generation, and distributing models across GPUs to improve processing capacity and response times.
Prepare training datasets for large language models with GPU-assisted cleaning. Covers duplicate removal, quality filtering, and personal information redaction, with workflows for text, images, video, and audio using NeMo Curator.
Helps speed up LLM text generation by comparing methods that predict and verify multiple tokens at once. Covers draft model selection, Medusa prediction heads, Lookahead Decoding settings, and deployment examples for inference services.
Explore local or remote repositories with Repomix CLI to understand their structure, locate related code across files, and review file counts and estimated tokens, the units AI models use to process text.
Configure LLM inference and serving on NVIDIA GPUs with TensorRT-LLM. Covers quantization, which reduces numerical precision, batching requests during generation, and distributing models across GPUs to improve processing capacity and response times.
Prepare training datasets for large language models with GPU-assisted cleaning. Covers duplicate removal, quality filtering, and personal information redaction, with workflows for text, images, video, and audio using NeMo Curator.
Helps fine-tune large language models with LoRA and QLoRA, methods that train small sets of additional parameters. Covers memory-conscious training, configuration choices, saving adapters, and switching task-specific adapters on a shared base model.
Refactor large SwiftUI screens into smaller views with clear inputs and state ownership. Organize actions, shared dependencies, and observable models while preserving existing layout and behavior, making the code easier to read and test.
Transcribe audio segments to text using Whisper models. Use larger models (small, base, medium, large-v3) for better accuracy, or faster-whisper for optimized performance. Always align transcription timestamps with diarization segments for accurate speaker-labeled subtitles.
The English summary is being prepared. Showing the original description.
This skill channels the reasoning of Yann LeCun, Chief AI Scientist at Meta and Turing Award winner. Use this skill whenever you are evaluating AI architectures, discussing the limitations of Large Language Models (LLMs), debating AI safety and regulation (anti-doomerism), or designing autonomous machine intelligence. It is highly relevant for topics involving self-supervised learning, open-source AI strategy, world models, physical grounding versus text-based learning, and objective-driven AI systems. Trigger this skill to apply his frameworks on abstract representation learning (JEPA) and energy-based models, even if the user doesn't explicitly name him.
The English summary is being prepared. Showing the original description.
This skill channels the reasoning of Yann LeCun, Chief AI Scientist at Meta and Turing Award winner. Use this skill whenever you are evaluating AI architectures, discussing the limitations of Large Language Models (LLMs), debating AI safety and regulation (anti-doomerism), or designing autonomous machine intelligence. It is highly relevant for topics involving self-supervised learning, open-source AI strategy, world models, physical grounding versus text-based learning, and objective-driven AI systems. Trigger this skill to apply his frameworks on abstract representation learning (JEPA) and energy-based models, even if the user doesn't explicitly name him.
The English summary is being prepared. Showing the original description.
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
The English summary is being prepared. Showing the original description.
Build or review Ruby on Rails applications by separating business operations, forms, and database queries into focused objects. Covers efficient data loading, background jobs, reusable view components, Hotwire interactions, and Rails 8 database-backed services.
Set up and optimize large language model inference, or response generation, on NVIDIA GPUs. Use quantization, batch processing, and multiple GPUs to improve serving performance, and expose models through a chat completion API.