Point card at per-variant repos (wyrmling-110M / -225M)

README.md

@@ -12,7 +12,17 @@ tags:
   - fan-content
 ---
 
-# wyrmling — a from-scratch intent→DSL model for Magic: The Gathering mechanics
+# 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
@@ -28,87 +38,5 @@ representation of Magic card mechanics. It speaks no English. The full story is
 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).
 
-## Variants
-
-| checkpoint | params | dims | layers | notes |
-| --- | --- | --- | --- | --- |
-| `wyrmling-110M` (v8f-p28) | 118M | d768 | 14 | the headline model |
-| `wyrmling-225M` (v8f-p28) | 226M | d1024 | 16 | size-ladder rung; same recipe, same data |
-
-Architecture: SwiGLU MLP, RoPE, QK-norm, untied embeddings, logit soft-cap.
-Optimizer: Muon + AdamW. Tokenizer: custom BPE, ~12k vocabulary, trained only on
-intent→DSL text so DSL concepts land as single semantically-loaded tokens.
-
-## Training
-
-- **Pretraining:** 18,000 steps (≈0.295B token-positions, ctx 512) on the v8 DSL
-  corpus mixed with 28% grammar-sampled rare-dense data — the optimum from the
-  rare-dense sweep (the anti-shadowing lever; see the blog's article 4).
-- **SFT:** 2 epochs (23,000 steps) on the v8 intent→DSL pairs.
-- A full cycle (pretrain + SFT) takes ≈4 h on one AMD R9700.
-
-## Evaluation
-
-One held-out v8 test (5,051 cards), free decode, matched generation budgets,
-Wald 95% CI (`docs/finetune/CROSS_TIER_EVAL.md` in the repo):
-
-| model | parse | canonical-exact | dsl_sim | tree_sim |
-| --- | --- | --- | --- | --- |
-| wyrmling-110M | 91.6% | 45.6% ±1.4 | 0.865 | 0.777 |
-| wyrmling-225M | 93.1% | 45.1% ±1.4 | 0.863 | 0.775 |
-
-Doubling parameters buys nothing here — the model is data-starved, not
-capacity-starved. That flat line is the point of the release.
-
-## Input / output format
-
-Input is a structured brief (not free prose), output is DSL:
-
-```
-Type: Artifact | Colors: W, R | Cost: {1}{W}{R} | Stats: 1/1
-Concept: A creature that gains power and toughness when equipped, and
-gains deathtouch if it is a Human and equipped. It costs {2} to equip.
-```
-
-```
-(card_abilities
-  (static (pt-mod (selector :type CREATURE :states (list EQUIPPED)) +1 +1))
-  (static (gain-ability (it) (DEATHTOUCH))
-          :condition (is-type :keyword AS :subtype HUMAN :subject-ref EQUIPPED_CREATURE))
-  (keyword EQUIP :cost ((mana "{2}"))))
-```
-
-Validate/render outputs with the MIT-licensed compiler in the repo.
-
-## Repository layout
-
-Each variant directory is self-contained:
-
-```
-wyrmling-110M/            wyrmling-225M/
-├── config.json           # WyrmlingHFConfig (vLLM plugin, MTG-E83)
-├── model.safetensors     # verbatim weight dump (embed.weight, blocks.N.attn.qkv.weight, …)
-├── tokenizer.json        # custom BPE, 12,034 entries incl. added tokens
-├── tokenizer_config.json
-└── wyrmling-sft-final.pt # original {config, model} training checkpoint
-```
-
-The `.pt` loads with the compiler repo's `TorchGCDGenerator.from_checkpoint()`
-(grammar-constrained decoding); the safetensors + config load through the
-repo's vLLM plugin (`src/wyrmling/`). Neither is a stock `transformers`
-architecture — you need the compiler repo either way.
-
-## Limitations (read before using)
-
-- **Shadowing:** nodes seen once in training are missed ~100% of the time; the
-  rare tail is the model's known failure mode and the subject of the research.
-- **Counterfeit-enum era:** the v8 training language still contained 117
-  counterfeit enum values (retired in
-  [!462](https://gitlab.com/Tagashy/mtg-compiler/-/merge_requests/462)); scores
-  above are measured on that same language. v9-trained checkpoints will
-  supersede these.
-- DSL only — no English, no card names, no flavor text, no art.
-- Intended for research on specialization/shadowing and for free fan content.
-  The MIT grant covers this project's rights in the weights; it does not license
-  Wizards of the Coast IP, and commercial use of that IP is not permitted by the
-  Fan Content Policy.
+Full model details, training recipe, evaluation, and limitations live on the
+per-variant cards linked above.