Backlinks: @TheVerseIsland + Biloxi Studios attribution

fb19b22 verified about 1 month ago

5.09 kB

license: apache-2.0
base_model: Qwen/Qwen3-Coder-30B-A3B-Instruct
tags:
  - verse
  - uefn
  - fortnite
  - unreal-editor-for-fortnite
  - code-generation
  - lora
  - peft
language:
  - en
library_name: peft
pipeline_tag: text-generation

Verse-Coder-30B-v1 — a UEFN Verse code LoRA

🌴 verseisland.com — learn Verse by exploring the island (built by the team behind this model) · @TheVerseIsland on X for v2 news and UEFN/Verse drops · built by Biloxi Studios

A LoRA adapter that teaches Qwen3-Coder-30B-A3B-Instruct to write Verse, the programming language of Unreal Editor for Fortnite (UEFN). Verse is scarce in open pre-training data, so base coder models default to Python/C#-shaped guesses for Verse prompts. This adapter fixes that — and it runs on a single RTX 4090.

Headline: on a compile-gated benchmark (real UEFN compiler, raw first-pass, no retries), the adapter passes 20% vs the identical base's 4% — a +400% relative improvement at the same quantization and hardware.

What it's for

Generating compilable Verse for UEFN gameplay: device scripts (creative_device), scene-graph components, and HUD/widget code from a plain-English task + the devices involved. It was built to power a Verse learning/authoring pipeline, and this V1 is released so the community can run a capable Verse model locally.

How it was trained

Base: Qwen/Qwen3-Coder-30B-A3B-Instruct (Apache-2.0, MoE).
Method: QLoRA (4-bit nf4), r=32, α=64, attention projections (q/k/v/o_proj), 2 epochs.
Data: ~900 supervised pairs + a raw Verse corpus — all compile-verified or first-party: device/API reference articles whose examples passed the real UEFN compiler, an API-surface Q/A set built from the UEFN digests, and Verse source. No scraped/unverified code.
Final train loss ≈ 0.95 (from ~2.1), token-accuracy ≈ 0.79.

Evaluation (the honest version)

Every candidate script is compiled on the real UEFN compiler. Metric = raw first-pass compile-pass rate, no escalation, no retries — the hardest, least-flattering bar. Test set = 50 device-diverse craft tasks spanning three paradigms (device-verse / scene-graph / widget); the numbers below are n=25.

The key control — same Q4 endpoint, LoRA on vs off (scale 0):

	compile-pass (raw first-pass, n=25)
Verse-Coder-30B-v1 (LoRA ON)	20% (5/25)
Qwen3-Coder-30B base (LoRA scale 0, same endpoint)	4% (1/25)
Δ (the adapter's contribution)	+16 pts / +400% relative

By paradigm (LoRA on): device-verse 22% · scene-graph 25% · widget 12% — it generalizes past devices, not a device-only model.

For scale: on this same harness, Claude Sonnet passes ~80–100% (the frontier ceiling), and a much larger production 35B base scores ~20% — i.e. this 4090-sized adapter matches a model class above its weight on Verse specifically.

What the adapter actually learned (one example)

A representative base failure — it doesn't know Verse's class syntax and writes it C#/Java-style:

# BASE (LoRA off):
class CountdownGame extends creative_device   # ← wrong language shape
→ Script error 3100: Unexpected "CountdownGame"

The adapter writes correct Verse:

# LoRA ON:
rune_portal_component := class(creative_device):
    @editable PortalTrigger : trigger_device = trigger_device{}
    OnBegin<override>()<suspends> : void =
        PortalTrigger.TriggeredEvent.Subscribe(OnPortalTriggered)

Caveat, stated plainly: this is a Q4_K_M quant on a single 4090 — the accessible-hardware configuration, not a quality ceiling. fp16/higher-quant serving is expected to score higher. 20% raw-first-pass is a floor; with a single compiler-error fix loop, ~half the near-misses (err=1) resolve.

Usage

Merge or apply the adapter to the base, or run the included GGUF (~52 MB) with llama.cpp against a Qwen3-Coder-30B-A3B GGUF:

./llama-server -m Qwen3-Coder-30B-A3B-Instruct-Q4_K_M.gguf \
  --lora verse-coder30b-v1-lora.gguf --ctx-size 40960

Prompt with a clear task + the UEFN devices involved. Ground it in real device APIs where you can — the model is strongest when told the exact device methods/events to use.

Limitations

Verse and UEFN evolve; APIs drift. Always compile in UEFN.
Q4 first-pass ~20% — treat output as a strong draft to compile-check + fix, not guaranteed-correct code.
Trained on gameplay-device Verse; niche APIs (advanced UI, scene-graph edge cases) are weaker.

License & attribution

Adapter released under Apache-2.0, matching the base Qwen/Qwen3-Coder-30B-A3B-Instruct. "Verse", "UEFN", and "Fortnite" are trademarks of Epic Games; this is an independent community model, not affiliated with or endorsed by Epic Games. Built by Verse Island — a Biloxi Studios Inc project (biloxistudios.com).