Ateliers · 01

Affinage refining

Training and fine-tuning open models on domain data, packaged as customised local models.

Affinage is the refining of molten metal: removing impurities until it reaches a specified composition.

Project site ↗ Repository ↗

Intended scope

  • Configuration-driven training and fine-tuning runs of open-weight models, full and parameter-efficient (for example LoRA), from a base model pinned to a commit hash.
  • Data preparation with a manifest and checksums, and a recorded split that Essai can check for train–test overlap.
  • A run record written next to every output.
  • Export of the result as a customised local model: merged safetensors weights, an adapter, or a quantised file for a local runtime, each with a model card.

Not in scope

Hosted training services; weight inspection and surgery (Burin); benchmark evaluation (Essai).

First milestones

  1. Run-record schema and writer, shared in form with Essai.
  2. A fine-tuning run on a tiny model and synthetic data that completes on CPU inside the test suite.
  3. Export with a generated model card.