Results for “supervised-learning”

Fine-tune a TAO model with standard supervised training, evaluation, and export, with AutoML bypass and platform-specific credential intake.

Fine-tune instruction-following LLMs with Unsloth's optimized SFTTrainer, covering dataset formatting, chat templates, training configuration, and thinking-model patterns.

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.

Trains and analyzes Sparse Autoencoders (SAEs) with SAELens to decompose neural network activations into interpretable features, covering loading pre-trained SAEs, training custom ones, and feature steering.

Design a spaced retrieval schedule for any topic list and timeline. Use when planning units, term sequences, or revision programmes.

Computer vision engineering skill for object detection, image segmentation, and visual AI systems. Covers CNN and Vision Transformer architectures, YOLO/Faster R-CNN/DETR detection, Mask R-CNN/SAM segmentation, and production deployment with ONNX/TensorRT. Includes PyTorch, torchvision, Ultralytics, Detectron2, and MMDetection frameworks. Use when building detection pipelines, training custom models, optimizing inference, or deploying vision systems.

Redesign a blocked topic sequence into an interleaved plan with mixed practice across related topics. Use when planning units, homework schedules, or revision programmes.

Visual Prompt Tuning

Train, evaluate, export, and run inference for Masked Auto-Encoder (MAE) models for self-supervised pretraining and fine-tuning of visual representations.

Train or fine-tune sentence-transformers models for retrieval, similarity, clustering, classification, and reranking, with support for bi-encoders, cross-encoders, and sparse encoders.

Build a library of metacognitive prompts targeting planning, monitoring, or evaluation for a specific task. Use when developing students' thinking-about-thinking during independent work.

Fine-tune and align language models using reinforcement learning with TRL, including SFT, DPO, PPO, GRPO, and reward model training.

Train and analyze Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features for mechanistic interpretability research.

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques for 1.5-3.6× speedup without quality loss.

Generate a scaffolded sequence of practice problems with graduated difficulty and strategic variability. Use when creating worksheets, homework sets, or independent practice materials.

Expert guidance for architecting, developing, and operating SurrealDB 3, covering SurrealQL, multi-model data modeling, vector search, security, deployment, performance tuning, SDK integration, and ecosystem tools.

Modify a classroom task with language scaffolds that preserve cognitive demand for EAL learners. Use when adapting existing tasks for students at different English proficiency levels.

Post-train LLMs with reinforcement learning using the slime framework, which integrates Megatron-LM for training and SGLang for rollout generation.

Build and evaluate machine learning models using scikit-learn for classification, regression, clustering, dimensionality reduction, and preprocessing.

Scales reinforcement learning with PufferLib — high-throughput parallel training (PuffeRL), vectorized environments, and native multi-agent systems achieving 2-10x speedups over standard implementations. Use when scaling RL to millions of steps per second, running vectorized or multi-agent setups, building custom PufferEnv tasks, or integrating game environments (Atari, Procgen, NetHack, PettingZoo). For standard single-agent algorithm implementations (PPO/SAC/DQN) or quick prototyping prefer alterlab-stable-baselines3. Part of the AlterLab Academic Skills suite.

Design a worked example fading sequence from fully worked examples through to independent practice. Use when teaching procedures, algorithms, or multi-step processes to novice learners.

Provides expert guidance for distributed training with DeepSpeed, covering ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, and sparse attention.

Nonlinear dimensionality reduction with UMAP — fast manifold learning for 2D/3D visualization, clustering preprocessing (e.g., HDBSCAN), and supervised or parametric UMAP. Use when projecting high-dimensional data to low dimensions for visualization, embedding generation, or as a preprocessing step before clustering. Part of the AlterLab Academic Skills suite.