Results for “pinata”

Fine-tune and deploy CLIP vision-language models for zero-shot classification, image-text retrieval, and embedding extraction with ONNX and TensorRT support.

Train quantum circuits with automatic differentiation and build hybrid quantum-classical models using PennyLane, including VQE, QAOA, and integration with PyTorch, JAX, and TensorFlow.

Create, read, manipulate, and store annotated data matrices using the AnnData Python package, designed for single-cell genomics and general-purpose annotated data workflows.

Fine-tune LLMs using LoRA, QLoRA, and PEFT with Hugging Face, including dataset preparation, hyperparameter tuning, evaluation, and deployment.

Train quantum circuits like neural networks with automatic differentiation, device-independent programming, and integration with PyTorch or JAX.

Add or upgrade PWA features to any web app: service worker, offline mode, install prompt, push notifications, and background sync. Use when asked to "make it a PWA", "offline support", "install prompt", "push notifications", "service worker", "add to home screen", "background sync", "Lighthouse PWA score", "app-like.

Trains LLMs with SimPO, a reference-free preference optimization method that outperforms DPO, using configurable hyperparameters and workflows for various models and tasks.

Use for writing, reviewing, debugging, testing, or analyzing Python SimPy discrete-event simulations. Trigger on Environment, Event, Process, timeout, Resource, PriorityResource, PreemptiveResource, Container, Store, queues, interrupts, simulation clocks, replications, or SimPy monitoring. Do not use for asyncio services, wall-clock schedulers, continuous ODE solvers, or Monte Carlo code without an event-process model.

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.