Results for “model-adaptation”

Provides an adaptive methodology for adding machine learning models to existing codebases, covering problem framing, data readiness, architectural decoupling, and baseline model integration.

Fine-tune large language models by training less than 1% of parameters using LoRA, QLoRA, and 25+ adapter methods, enabling efficient adaptation on limited GPU memory.

Visual Prompt Tuning

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

Fine-tune open models or Gemini models using Agent Platform infrastructure, from environment setup through data preparation, job configuration, monitoring, and deployment.

Large Language Model development, training, fine-tuning, and deployment best practices.

TRAK: Attributing Model Behavior at Scale

database-model-standards

Runs directional ablation and refusal-direction analysis for open-weight models the user may modify; use to reduce benign over-refusal or measure refusal/KL trade-offs, not for training.

Build and sharpen a project's domain model — a CONTEXT.md glossary and ubiquitous language. Use when pinning down terminology, or the agent "uses the wrong words". Repo decision-memory system (INDEX.md, rejected alternatives) → docs-adr.

"Make it interpretable" is four different requests.

Dolphins: Multimodal Language Model for Driving

A model in production is never just weights.

Model-trader version compatibility protocol: Embed version metadata in checkpoints, validate at load time. Trigger when: (1) training and live trading versions diverge, (2) models fail to load, (3) action interpretation issues.

Adapt a classroom task for specific learner needs while preserving the core learning objective intact. Use when differentiating for SEND, EAL, gifted, ADHD, dyslexia, or anxiety.

Design an adaptive assessment loop where each student response triggers the next instructional move. Use when building technology-enhanced formative assessment cycles.

Selects the right Gemma model for a task, recommends deployment tooling (Gradio, Transformers.js, Vertex AI, MLX), and applies optimizations like MTP and QAT.

Train machine learning models end-to-end, covering data loading, preprocessing, architecture selection, training loops, validation, and checkpointing. Use when the user requests model training or provides relevant inputs for this workflow.

BDI (Beliefs-Desires-Intentions) agency framework for designing autonomous agents with mental state architectures

Alpaca: A Strong, Replicable Instruction-Following Model

Fine-tune large language models by training less than 1% of parameters using LoRA, QLoRA, and 25+ adapter methods, enabling efficient adaptation on consumer GPUs.