Skip to main content
Models power your AI applications. Add a model to a project to deploy it, then make inference requests. A model in your project comes from one of four sources:
SourceWhen to use
Adaptive catalog (new in v0.14)The fastest path. A curated, server-managed list of production-validated open-source models (Mistral, Qwen, Gemma families across sizes). No HF token, no manual download.
Hugging Face importA specific HF model that isn’t in the catalog. Requires an HF token.
External providerOpenAI, Anthropic, Gemini, Azure, or your own API endpoint. See Integrations.
Promoted checkpointA snapshot from a training run, lifted into the registry as a standalone model. See Promoted checkpoints below.
The catalog is the recommended default. New models appear there server-side without requiring a platform update.

​
Add and deploy a model

Once a model is in your project’s registry, deploy it for inference:
adaptive.models.add_to_project(model="llama-3.1-8b-instruct")
adaptive.models.deploy(model="llama-3.1-8b-instruct", wait=True)

# Or use attach() to do both in one call
adaptive.models.attach(model="llama-3.1-8b-instruct", wait=True)
ParameterTypeRequiredDescription
modelstrYesModel key from the registry
waitboolNoBlock until model is online (default: False)
make_defaultboolNoSet as default model for the project
The model becomes available within a few minutes.

​
Import from Hugging Face

For models not in the Adaptive catalog, import from Hugging Face directly:
adaptive.models.add_hf_model(
    hf_model_id="meta-llama/Llama-3.1-8B-Instruct",
    output_model_name="My Llama 3.1 8B",
    output_model_key="my-llama-3.1-8b",
    hf_token="hf_...",
)
ParameterTypeRequiredDescription
hf_model_idstrYesFull HF model ID (must be in the supported list)
output_model_namestrYesDisplay name for the imported model
output_model_keystrYesKey for the imported model in the Adaptive registry
hf_tokenstrYesHugging Face access token with read permission
compute_poolstrNoCompute pool to run the import job
Import runs as an asynchronous job — the model appears in the registry once conversion finishes.
Catalog import (the recommended path) is currently UI-only. Open the Add Model dialog in your project and pick Import from Adaptive ML’s catalog.
A training run saves snapshots at configurable intervals (see checkpoint_frequency). Any saved checkpoint can be promoted to a standalone model in the registry, then evaluated or deployed like any imported model.Promotion is currently UI-only — open a run and pick Promote checkpoint on a saved checkpoint. SDK support uses the underlying GraphQL mutation directly:
from adaptive_sdk.graphql_client import PromoteCheckpointInput, CheckpointModelPromotionInput

job = adaptive._gql_client.promote_checkpoint(
    input=PromoteCheckpointInput(
        artifact_id="<checkpoint-artifact-uuid>",
        models=[CheckpointModelPromotionInput(
            model_key="<source-model-key-in-checkpoint>",
            name="my-grpo-step-800",
        )],
    )
)
Promotion runs as an asynchronous copy job. Promoted models retain full provenance back to the source run.
LoRA backbone footgun: when you promote a LoRA checkpoint, the platform records the backbone reference in the model’s metadata but does not automatically attach the backbone to your project. If the backbone isn’t already in the project, inference against the promoted LoRA fails with a “model not found” error. Add the backbone with add_to_project before deploying.
See SDK Reference for all model methods.