技能库 177 个

Spaced-repetition flashcard system. Create cards from facts or text, chat with flashcards using free-text answers graded

Publish static sites to {slug}.here.now and store private files in cloud Drives for agent-to-agent handoff.

Canvas LMS integration — fetch enrolled courses and assignments using API token authentication.

OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and lan

Unsloth: 2-5x faster LoRA/QLoRA fine-tuning, less VRAM.

TRL: SFT, DPO, PPO, GRPO, reward modeling for LLM RLHF.

Axolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO).

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when p

Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on

State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating im

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models,

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activa

High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems r

High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system,

DSPy: declarative LM programs, auto-optimize prompts, RAG.

Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU of

Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse)

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B)

GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faste

Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure ma

Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP visi

Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with

Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse compl