Part 1 · Model Factory

Understand what weights are, how training creates them, and how product choices become a deployable model artifact.

From checkpoint to deployable inputs · 7 min

Package the model artifact

Serving needs weights plus configuration, tokenizer files, and enough metadata to reconstruct the model correctly.

Essential path

Plain language, the core causal flow, and required checks.

Package what serving needs

A deployable model normally contains weight shards, architecture configuration, tokenizer assets, numeric-format information, and an immutable manifest tying the pieces to one version. Integrity and compatibility checks prevent a partial or mixed release from being marked ready.

The artifact is the handoff between the model factory and the inference system.

Open, closed, and what is actually released

  • Closed service: the provider exposes an API; the weights remain private.
  • Open weights: the parameter files can be downloaded, but the original data and complete training recipe may remain private.
  • Open-ish: weights are available under use, scale, or redistribution restrictions.
  • Reproducibly open: weights, code, recipe, and usable data provenance are available under compatible rights.

Inspect a model release spectrum

Core + Expert

Model release contents

Inspect what a model release actually gives you

interactive explanation

Open versus closed is a spectrum of artifacts, rights, operational control, and withheld know-how.

Release typeWeightsArchitectureTraining dataTraining codeRecipe
Closed APINot providedNot providedNot providedNot providedNot provided
Open weightsIncludedIncludedNot providedNot providedNot provided
Open-ishIncludedIncludedNot providedIncludedNot provided
Reproducible openIncludedIncludedIncludedIncludedIncluded

Endpoint access; provider owns every layer.

Owning weights buys control, permanence, and modification. It also makes quantization, batching, KV-cache management, scaling, evaluation, security, and version lifecycle your responsibility. “Free to download” does not mean free to operate.

After this chapter, you can:
  • Name the main pieces of a model artifact.
  • Explain why artifact compatibility matters.
  • Weight shards hold learned tensors.
  • Configuration describes the architecture.
  • Tokenizer assets map text and token IDs.
  • Runtime metadata records formats and compatibility.

Which item is required alongside weights to map text to token IDs?