Loading...
Loading...
Found 42 Skills
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.
PyTorch, TensorFlow, neural networks, CNNs, transformers, and deep learning for production
Use when "HuggingFace Transformers", "pre-trained models", "pipeline API", or asking about "text generation", "text classification", "question answering", "NER", "fine-tuning transformers", "AutoModel", "Trainer API"
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.
Universal Runtime best practices for PyTorch inference, Transformers models, and FastAPI serving. Covers device management, model loading, memory optimization, and performance tuning.
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.
Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.
GENERator DNA 序列生成模型的昇腾 NPU 迁移 Skill，适用于将基于 HuggingFace Transformers 的 Causal LM 从 CUDA 迁移到华为 Ascend NPU，覆盖环境搭建、依赖安装、代码适配、多进程处理和 sequence recovery 验证。
Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.
Post-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduction with <2% perplexity degradation, or for faster inference (3-4× speedup) vs FP16. Integrates with transformers and PEFT for QLoRA fine-tuning.
Provides guidance for writing and benchmarking optimized CUDA kernels for NVIDIA GPUs (H100, A100, T4) targeting HuggingFace diffusers and transformers libraries. Supports models like LTX-Video, Stable Diffusion, LLaMA, Mistral, and Qwen. Includes integration with HuggingFace Kernels Hub (get_kernel) for loading pre-compiled kernels. Includes benchmarking scripts to compare kernel performance against baseline implementations.
Elite AI/ML Senior Engineer with 20+ years experience. Transforms Claude into a world-class AI researcher and engineer capable of building production-grade ML systems, LLMs, transformers, and computer vision solutions. Use when: (1) Building ML/DL models from scratch or fine-tuning, (2) Designing neural network architectures, (3) Implementing LLMs, transformers, attention mechanisms, (4) Computer vision tasks (object detection, segmentation, GANs), (5) NLP tasks (NER, sentiment, embeddings), (6) MLOps and production deployment, (7) Data preprocessing and feature engineering, (8) Model optimization and debugging, (9) Clean code review for ML projects, (10) Choosing optimal libraries and frameworks. Triggers: "ML", "AI", "deep learning", "neural network", "transformer", "LLM", "computer vision", "NLP", "TensorFlow", "PyTorch", "sklearn", "train model", "fine-tune", "embedding", "CNN", "RNN", "LSTM", "attention", "GPT", "BERT", "diffusion", "GAN", "object detection", "segmentation".