Skip to content
OpenPond
Join community
Overview/What you can do

What you can do

Train, modify, evaluate and serve models, and configure supported continual-learning policies.

OpenPond is a lab for model training, adapters and continual learning. Ponder Training connects reviewed data, training runs, independent evaluation, saved Model versions and serving. Choose a workflow, then the adapter and starting model for the behavior you want to improve.

Choose a workflow and adapter

WorkflowCurrent adaptersPurpose
SFTLoRA, Engram, Neuron trainingLearn from reviewed answer examples through the selected adapter's trainer.
RLLoRALearn from rewards using GRPO.
Decision ModelSpecialized LoRATrain or score allowed choices from structured state.

See the adapter support matrix for supported and unsupported pairs and exact model/runtime requirements. Workflow and adapter choices can be saved as an authoring draft. Unsupported pairs cannot execute; selecting an adapter does not establish runtime availability.

Continual learning

Workflow / adapterContinual learningManual parent continuation
SFT / LoRAYesGeneric cross-job checkpoint continuation is unavailable.
SFT / EngramNoExact compatible memory module with a fresh optimizer.
SFT / Neuron trainingNoUnavailable; saved patches support inference.
RL / LoRAYesShared, Stacked or Merged LoRA under exact-parent constraints.
Decision Model / LoRANoExact compatible adapter with a fresh optimizer.

Scheduled learning, manual continuation and interrupted-run recovery are separate capabilities. A schedule does not authorize candidate acceptance or serving. Continual learning explains those boundaries.

The model workflow

ObjectWhat it holds
DatasetVersioned tasks, references, provenance, graders and train/holdout roles.
ExperimentA configured test and its retained evidence; training history remains under Models → Runs.
WorkflowSFT, RL or Decision Model: the learning approach or scoring task.
AdapterLoRA, Engram or Neuron training: the parameters or added memory that learn, under their exact compatibility rules.
ModelSaved versions with exact artifacts, lineage and a canonical learning policy.
Continual learningScheduled checks and supported updates from eligible new evidence, with budgets, independent comparison and candidate decisions.
ServingA separately authorized deployment of a compatible qualified version.

SFT learns from reviewed demonstrations; GRPO learns from rewards on fresh attempts. An adapter's availability depends on the exact model and runtime. Continual learning repeats only supported training paths; a visible method does not imply that it can run on a schedule.

A new Dataset row or conversation does not change model weights. Ordinary Model evidence needs explicit human admission. Conversation policies can admit independently verified examples under their saved rules, routing exceptions to Inbox. Candidate acceptance and serving activation remain separate from example approval.

Start with a measured workflow

  1. Create or import a Dataset, retain its provenance and separate training from held-out examples.
  2. Validate the Graders and run a baseline Experiment.
  3. Choose training or a compatible modification based on the failure. Review exact inputs, runtime and spending before execution.
  4. Compare the candidate on independent tasks and save the versions you accept.
  5. Serve a qualified version, or configure a supported continual-learning policy to check for future eligible batches.

Workspaces and Projects

A workspace sets membership and access. A Console Project groups Models, Datasets, graders, experiments and training resources. Choose your workspace before opening a resource; use the Project picker to narrow the collection. Grouping resources does not change their versions or publish them.

Tools around the model workflow

Use the SDK for programmatic integration, Evals for portable task and scoring contracts, and Harness for versioned agent instructions and tools. Desktop works with local projects and evidence; Cloud provides hosted inference, compute, storage and services.

Pal is the assistant available in OpenPond's Chat and Work surfaces. A Pal conversation and Harness refinement have their own tools and permissions; neither automatically trains a Ponder model. Connected agent activity can supply reviewed evidence for a separately configured learning workflow.

Next: Choose your starting point. Check availability for exact execution and account requirements.

View as Markdown