---
license: mit
language:
  - en
pipeline_tag: text-generation
tags:
  - mtg
  - magic-the-gathering
  - dsl
  - from-scratch
  - small-language-model
  - fan-content
---

# wyrmling — moved to per-variant repositories

This repo has been split so each checkpoint has its files at the repo root:

| checkpoint | repository |
| --- | --- |
| `wyrmling-110M` — the headline model | [Tagashy/wyrmling-110M-mtg-dsl](https://huggingface.co/Tagashy/wyrmling-110M-mtg-dsl) |
| `wyrmling-225M` — size-ladder rung | [Tagashy/wyrmling-225M-mtg-dsl](https://huggingface.co/Tagashy/wyrmling-225M-mtg-dsl) |

The weights here are unchanged and still load, so existing links and scripts keep
working — but new work should use the per-variant repos above.

**wyrmling is unofficial Fan Content permitted under the
[Fan Content Policy](https://company.wizards.com/en/legal/fancontentpolicy). Not
approved/endorsed by Wizards. Portions of the materials used are property of
Wizards of the Coast. © Wizards of the Coast LLC.** Card data provided by
[Scryfall](https://scryfall.com). Not affiliated with either.

wyrmling is a tiny decoder-only language model built entirely from scratch — its
own architecture, its own tokenizer, no inherited weights — for exactly one task:
translating a structured card *intent* into the
[mtg-compiler](https://gitlab.com/Tagashy/mtg-compiler) DSL, a typed s-expression
representation of Magic card mechanics. It speaks no English. The full story is in
the blog series [*Teaching a model to write Magic cards by building the compiler
first*](https://blog.deadgate.fr/stories/mtg-compiler/), especially article 4 (shadowing).

Full model details, training recipe, evaluation, and limitations live on the
per-variant cards linked above.