Loading...
Loading...
Found 74 Skills
Response Transformer - Auto-activating skill for API Integration. Triggers on: response transformer, response transformer Part of the API Integration skill category.
When the user wants to forecast using deep learning, LSTMs, transformers, or neural networks. Also use when the user mentions "neural network forecasting," "LSTM," "GRU," "transformer forecasting," "attention mechanisms," "seq2seq," "temporal convolution," "deep learning time series," or complex non-linear patterns. For traditional forecasting, see demand-forecasting. For general ML, see ml-supply-chain.
Universal Runtime best practices for PyTorch inference, Transformers models, and FastAPI serving. Covers device management, model loading, memory optimization, and performance tuning.
Expert guidance for natural language processing development using transformers, spaCy, NLTK, and modern NLP techniques.
Expert guidance for working with Hugging Face Transformers library for NLP, computer vision, and multimodal AI tasks.
Guidance for setting up HuggingFace model inference services with Flask APIs. This skill applies when downloading HuggingFace models, creating inference endpoints, or building ML model serving APIs. Use for tasks involving transformers library, model caching, and REST API creation for ML models.
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.
Validate and use CUDA graph capture in Megatron Bridge, including local full-iteration graphs and Transformer Engine scoped graphs for attention, MLP, and MoE modules.
PyTorch deep learning development with transformers, diffusion models, and GPU optimization.
Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.
Convert HuggingFace transformer models to ONNX format for browser inference with Transformers.js and WebGPU. Use when given a HuggingFace model link to convert to ONNX, when setting up optimum-cli for ONNX export, when quantizing models (fp16, q8, q4) for web deployment, when configuring Transformers.js with WebGPU acceleration, or when troubleshooting ONNX conversion errors. Triggers on mentions of ONNX conversion, Transformers.js, WebGPU inference, optimum export, model quantization for browser, or running ML models in the browser.