159 skills · sorted by relevance
Use when writing HIP kernels with hipcc, porting CUDA code through HIPIFY, profiling with rocprofv3, debugging with rocgdb, or optimizing for MI300X. Not for NVIDIA-side kernels: use cuda.
The English summary is being prepared. Showing the original description.
Use when writing, optimizing, or benchmarking a C++ CPU kernel with AVX2 or AVX512 intrinsics for the Hugging Face kernels ecosystem. Not for CUDA kernels: use cuda.
The English summary is being prepared. Showing the original description.
窓際族物語の動画を、チャプター毎のキーフレーム画像を作らずに「プロンプト＋キャラクターシート＋セリフ音声」だけでMiniMax H3（R2V）に生成させるワークフロー。ユーザーから「画像なしで動画を作って」「キーフレームなしで動画を作って」「シートだけで動画を作って」と指示されたときに必ず使用する。大まかな指示→チャプター分割案→チャプター毎の動きを人間に確認→全チャプター確定→プロンプト作成の順で進め、確定前にプロンプトを書かない。画風の注意文はチャプターに映るものだけを最小限で書き、モブキャラはラン専用のキャラクターシートを作って渡す。動画生成の実行先は/colab-video（Colab）または/local-videoステップ7（ローカルCUDA）。
The English summary is being prepared. Showing the original description.
Helps write and review PyTorch models, training loops, and data loading code. Covers repeatable experiments, saving training progress, and techniques for reducing GPU memory use or improving training speed, with practical code examples.
Guide language model training with TRL using example answers, preferred response pairs, or reward scores. The skill covers data preparation, method selection, reward model training, evaluation, and adjustments for memory limits or unstable training.
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.
Prepare LLM training datasets with NeMo Curator by removing duplicates, filtering low-quality content, and redacting personal information. The skill also covers image, video, and audio curation, including GPU processing and distributed workflows.
Analyze and modify refusal behavior in open-weight language models without retraining. Use OBLITERATUS to select methods suited to available hardware, compare approaches, and evaluate changes in refusal rates and response quality.
Create Python workflows for generating images from text, restyling existing pictures, and filling selected regions. Using HuggingFace Diffusers, the skill explains composition controls, style adapters, generation settings, and ways to reduce memory use.
Use AudioCraft to generate music, sound effects, and environmental audio from text descriptions. Follow implementation examples for model selection, melody and reference audio guidance, stereo output, batch generation, and saving audio files.
Generate complete songs locally from lyrics and tags describing mood, instruments, or genre. The skill guides setup, input formatting, memory-saving settings, and MP3 output using the open-source HeartMuLa music models.
Plan and review PufferLib reinforcement learning workflows, where agents learn through rewards. Covers version-specific environment checks, parallel execution, training and evaluation plans, plus checkpoint inspection before loading saved models.
Generate candidate positions and orientations for small molecules binding to proteins with DiffDock and DiffDock-L. Prepare single or batch docking runs, organize predicted poses by model confidence, and review validation needs without treating confidence as binding affinity.
Investigate SGLang serving failures by collecting server state, preserving failing requests, and replaying them on a clean target. Summarize evidence and likely causes, then choose the next debugging tool for crashes, stalls, or performance regressions.
Organize SGLang GPU operations when adding or moving code. It guides API placement, operation registration, test organization, and migration checks to preserve existing behavior, references, and continuous integration coverage.
Build and debug sglang tests comparing token probabilities during prompt processing and step-by-step generation. Separate numerical differences from reused-state bugs, choose test thresholds, and locate the first operation that diverges.
Investigate phishing emails that hide malicious links in QR codes. Decode destinations, analyze suspicious URLs, configure email detection rules, and plan mobile protections and awareness training for people who scan codes on their phones.
Guide language model training with TRL, from learning to follow instructions to matching human preferences. Covers method selection, training data, reward models that score responses, evaluation, and adjustments for memory limits or unstable training.
Convert LLMs to GGUF and reduce model size through quantization, which stores weights at lower numerical precision. Prepare models for CPU or Apple Silicon inference, compare compression levels, and integrate them with local AI tools.
Use SAELens to train and analyze sparse autoencoders, which separate neural network activity into features that may represent recognizable concepts. Explore pretrained features, evaluate reconstruction quality, and investigate how individual features influence language model outputs.
Run machine learning workloads on Modal's cloud GPUs without managing servers. Guides Python configuration for training, inference, batch processing, and API deployment, including automatic scaling, persistent storage, scheduled jobs, and troubleshooting.
Build and evaluate Mamba models for long sequences using state-space models, which summarize past inputs in an internal state. Covers setup, pretrained text generation, differences between Mamba-1 and Mamba-2, and speed comparisons with Transformers.
Build image captioning, visual question answering, and text-based image search with BLIP-2. The skill explains model selection, batch processing, and memory-saving settings, with Python examples for connecting image understanding to language models.
Guides the use of RWKV, a language model architecture that carries information forward in a compact state. Covers streaming text generation, long document processing, fine-tuning, and memory comparisons with Transformers.